#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/module.h>
-#include <linux/kallsyms.h>
#include <linux/netpoll.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
#include <linux/if_arp.h>
#include <linux/if_vlan.h>
#include <linux/ip.h>
+#include <net/ip.h>
#include <linux/ipv6.h>
#include <linux/in.h>
#include <linux/jhash.h>
#include "net-sysfs.h"
+/* Instead of increasing this, you should create a hash table. */
+#define MAX_GRO_SKBS 8
+
/*
* The list of packet types we will receive (as opposed to discard)
* and the routines to invoke.
ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,
ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
ARPHRD_FCFABRIC, ARPHRD_IEEE802_TR, ARPHRD_IEEE80211,
- ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_VOID,
- ARPHRD_NONE};
+ ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET,
+ ARPHRD_PHONET_PIPE, ARPHRD_VOID, ARPHRD_NONE};
static const char *netdev_lock_name[] =
{"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
"_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
"_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
"_xmit_FCFABRIC", "_xmit_IEEE802_TR", "_xmit_IEEE80211",
- "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_VOID",
- "_xmit_NONE"};
+ "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET",
+ "_xmit_PHONET_PIPE", "_xmit_VOID", "_xmit_NONE"};
static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];
* Change name of a device, can pass format strings "eth%d".
* for wildcarding.
*/
-int dev_change_name(struct net_device *dev, char *newname)
+int dev_change_name(struct net_device *dev, const char *newname)
{
char oldname[IFNAMSIZ];
int err = 0;
err = dev_alloc_name(dev, newname);
if (err < 0)
return err;
- strcpy(newname, dev->name);
}
else if (__dev_get_by_name(net, newname))
return -EEXIST;
strlcpy(dev->name, newname, IFNAMSIZ);
rollback:
- err = device_rename(&dev->dev, dev->name);
- if (err) {
- memcpy(dev->name, oldname, IFNAMSIZ);
- return err;
+ /* For now only devices in the initial network namespace
+ * are in sysfs.
+ */
+ if (net == &init_net) {
+ ret = device_rename(&dev->dev, dev->name);
+ if (ret) {
+ memcpy(dev->name, oldname, IFNAMSIZ);
+ return ret;
+ }
}
write_lock_bh(&dev_base_lock);
}
/**
+ * dev_set_alias - change ifalias of a device
+ * @dev: device
+ * @alias: name up to IFALIASZ
+ * @len: limit of bytes to copy from info
+ *
+ * Set ifalias for a device,
+ */
+int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
+{
+ ASSERT_RTNL();
+
+ if (len >= IFALIASZ)
+ return -EINVAL;
+
+ if (!len) {
+ if (dev->ifalias) {
+ kfree(dev->ifalias);
+ dev->ifalias = NULL;
+ }
+ return 0;
+ }
+
+ dev->ifalias = krealloc(dev->ifalias, len+1, GFP_KERNEL);
+ if (!dev->ifalias)
+ return -ENOMEM;
+
+ strlcpy(dev->ifalias, alias, len+1);
+ return len;
+}
+
+
+/**
* netdev_features_change - device changes features
* @dev: device to cause notification
*
*/
int dev_open(struct net_device *dev)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
int ret = 0;
ASSERT_RTNL();
*/
set_bit(__LINK_STATE_START, &dev->state);
- if (dev->validate_addr)
- ret = dev->validate_addr(dev);
+ if (ops->ndo_validate_addr)
+ ret = ops->ndo_validate_addr(dev);
- if (!ret && dev->open)
- ret = dev->open(dev);
+ if (!ret && ops->ndo_open)
+ ret = ops->ndo_open(dev);
/*
* If it went open OK then:
*/
int dev_close(struct net_device *dev)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
ASSERT_RTNL();
might_sleep();
* We allow it to be called even after a DETACH hot-plug
* event.
*/
- if (dev->stop)
- dev->stop(dev);
+ if (ops->ndo_stop)
+ ops->ndo_stop(dev);
/*
* Device is now down.
}
-void __netif_schedule(struct Qdisc *q)
+static inline void __netif_reschedule(struct Qdisc *q)
{
- if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) {
- struct softnet_data *sd;
- unsigned long flags;
+ struct softnet_data *sd;
+ unsigned long flags;
- local_irq_save(flags);
- sd = &__get_cpu_var(softnet_data);
- q->next_sched = sd->output_queue;
- sd->output_queue = q;
- raise_softirq_irqoff(NET_TX_SOFTIRQ);
- local_irq_restore(flags);
- }
+ local_irq_save(flags);
+ sd = &__get_cpu_var(softnet_data);
+ q->next_sched = sd->output_queue;
+ sd->output_queue = q;
+ raise_softirq_irqoff(NET_TX_SOFTIRQ);
+ local_irq_restore(flags);
+}
+
+void __netif_schedule(struct Qdisc *q)
+{
+ if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state))
+ __netif_reschedule(q);
}
EXPORT_SYMBOL(__netif_schedule);
__be16 type = skb->protocol;
int err;
- BUG_ON(skb_shinfo(skb)->frag_list);
-
skb_reset_mac_header(skb);
skb->mac_len = skb->network_header - skb->mac_header;
__skb_pull(skb, skb->mac_len);
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ prefetch(&dev->netdev_ops->ndo_start_xmit);
if (likely(!skb->next)) {
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(skb, dev);
goto gso;
}
- return dev->hard_start_xmit(skb, dev);
+ return ops->ndo_start_xmit(skb, dev);
}
gso:
skb->next = nskb->next;
nskb->next = NULL;
- rc = dev->hard_start_xmit(nskb, dev);
+ rc = ops->ndo_start_xmit(nskb, dev);
if (unlikely(rc)) {
nskb->next = skb->next;
skb->next = nskb;
{
u32 addr1, addr2, ports;
u32 hash, ihl;
- u8 ip_proto;
+ u8 ip_proto = 0;
if (unlikely(!simple_tx_hashrnd_initialized)) {
get_random_bytes(&simple_tx_hashrnd, 4);
}
switch (skb->protocol) {
- case __constant_htons(ETH_P_IP):
- ip_proto = ip_hdr(skb)->protocol;
+ case htons(ETH_P_IP):
+ if (!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)))
+ ip_proto = ip_hdr(skb)->protocol;
addr1 = ip_hdr(skb)->saddr;
addr2 = ip_hdr(skb)->daddr;
ihl = ip_hdr(skb)->ihl;
break;
- case __constant_htons(ETH_P_IPV6):
+ case htons(ETH_P_IPV6):
ip_proto = ipv6_hdr(skb)->nexthdr;
addr1 = ipv6_hdr(skb)->saddr.s6_addr32[3];
addr2 = ipv6_hdr(skb)->daddr.s6_addr32[3];
static struct netdev_queue *dev_pick_tx(struct net_device *dev,
struct sk_buff *skb)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
u16 queue_index = 0;
- if (dev->select_queue)
- queue_index = dev->select_queue(dev, skb);
+ if (ops->ndo_select_queue)
+ queue_index = ops->ndo_select_queue(dev, skb);
else if (dev->real_num_tx_queues > 1)
queue_index = simple_tx_hash(dev, skb);
spin_lock(root_lock);
- rc = qdisc_enqueue_root(skb, q);
- qdisc_run(q);
-
+ if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
+ kfree_skb(skb);
+ rc = NET_XMIT_DROP;
+ } else {
+ rc = qdisc_enqueue_root(skb, q);
+ qdisc_run(q);
+ }
spin_unlock(root_lock);
- rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc;
goto out;
}
EXPORT_SYMBOL(netif_rx_ni);
-static inline struct net_device *skb_bond(struct sk_buff *skb)
-{
- struct net_device *dev = skb->dev;
-
- if (dev->master) {
- if (skb_bond_should_drop(skb)) {
- kfree_skb(skb);
- return NULL;
- }
- skb->dev = dev->master;
- }
-
- return dev;
-}
-
-
static void net_tx_action(struct softirq_action *h)
{
struct softnet_data *sd = &__get_cpu_var(softnet_data);
head = head->next_sched;
- smp_mb__before_clear_bit();
- clear_bit(__QDISC_STATE_SCHED, &q->state);
-
root_lock = qdisc_lock(q);
if (spin_trylock(root_lock)) {
+ smp_mb__before_clear_bit();
+ clear_bit(__QDISC_STATE_SCHED,
+ &q->state);
qdisc_run(q);
spin_unlock(root_lock);
} else {
- __netif_schedule(q);
+ if (!test_bit(__QDISC_STATE_DEACTIVATED,
+ &q->state)) {
+ __netif_reschedule(q);
+ } else {
+ smp_mb__before_clear_bit();
+ clear_bit(__QDISC_STATE_SCHED,
+ &q->state);
+ }
}
}
}
q = rxq->qdisc;
if (q != &noop_qdisc) {
spin_lock(qdisc_lock(q));
- result = qdisc_enqueue_root(skb, q);
+ if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
+ result = qdisc_enqueue_root(skb, q);
spin_unlock(qdisc_lock(q));
}
{
struct packet_type *ptype, *pt_prev;
struct net_device *orig_dev;
+ struct net_device *null_or_orig;
int ret = NET_RX_DROP;
__be16 type;
+ if (skb->vlan_tci && vlan_hwaccel_do_receive(skb))
+ return NET_RX_SUCCESS;
+
/* if we've gotten here through NAPI, check netpoll */
if (netpoll_receive_skb(skb))
return NET_RX_DROP;
if (!skb->iif)
skb->iif = skb->dev->ifindex;
- orig_dev = skb_bond(skb);
-
- if (!orig_dev)
- return NET_RX_DROP;
+ null_or_orig = NULL;
+ orig_dev = skb->dev;
+ if (orig_dev->master) {
+ if (skb_bond_should_drop(skb))
+ null_or_orig = orig_dev; /* deliver only exact match */
+ else
+ skb->dev = orig_dev->master;
+ }
__get_cpu_var(netdev_rx_stat).total++;
rcu_read_lock();
/* Don't receive packets in an exiting network namespace */
- if (!net_alive(dev_net(skb->dev)))
+ if (!net_alive(dev_net(skb->dev))) {
+ kfree_skb(skb);
goto out;
+ }
#ifdef CONFIG_NET_CLS_ACT
if (skb->tc_verd & TC_NCLS) {
#endif
list_for_each_entry_rcu(ptype, &ptype_all, list) {
- if (!ptype->dev || ptype->dev == skb->dev) {
+ if (ptype->dev == null_or_orig || ptype->dev == skb->dev ||
+ ptype->dev == orig_dev) {
if (pt_prev)
ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = ptype;
list_for_each_entry_rcu(ptype,
&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
if (ptype->type == type &&
- (!ptype->dev || ptype->dev == skb->dev)) {
+ (ptype->dev == null_or_orig || ptype->dev == skb->dev ||
+ ptype->dev == orig_dev)) {
if (pt_prev)
ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = ptype;
}
}
+static int napi_gro_complete(struct sk_buff *skb)
+{
+ struct packet_type *ptype;
+ __be16 type = skb->protocol;
+ struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
+ int err = -ENOENT;
+
+ if (!skb_shinfo(skb)->frag_list)
+ goto out;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ptype, head, list) {
+ if (ptype->type != type || ptype->dev || !ptype->gro_complete)
+ continue;
+
+ err = ptype->gro_complete(skb);
+ break;
+ }
+ rcu_read_unlock();
+
+ if (err) {
+ WARN_ON(&ptype->list == head);
+ kfree_skb(skb);
+ return NET_RX_SUCCESS;
+ }
+
+out:
+ __skb_push(skb, -skb_network_offset(skb));
+ return netif_receive_skb(skb);
+}
+
+void napi_gro_flush(struct napi_struct *napi)
+{
+ struct sk_buff *skb, *next;
+
+ for (skb = napi->gro_list; skb; skb = next) {
+ next = skb->next;
+ skb->next = NULL;
+ napi_gro_complete(skb);
+ }
+
+ napi->gro_list = NULL;
+}
+EXPORT_SYMBOL(napi_gro_flush);
+
+int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+{
+ struct sk_buff **pp = NULL;
+ struct packet_type *ptype;
+ __be16 type = skb->protocol;
+ struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
+ int count = 0;
+ int same_flow;
+ int mac_len;
+
+ if (!(skb->dev->features & NETIF_F_GRO))
+ goto normal;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ptype, head, list) {
+ struct sk_buff *p;
+
+ if (ptype->type != type || ptype->dev || !ptype->gro_receive)
+ continue;
+
+ skb_reset_network_header(skb);
+ mac_len = skb->network_header - skb->mac_header;
+ skb->mac_len = mac_len;
+ NAPI_GRO_CB(skb)->same_flow = 0;
+ NAPI_GRO_CB(skb)->flush = 0;
+
+ for (p = napi->gro_list; p; p = p->next) {
+ count++;
+ NAPI_GRO_CB(p)->same_flow =
+ p->mac_len == mac_len &&
+ !memcmp(skb_mac_header(p), skb_mac_header(skb),
+ mac_len);
+ NAPI_GRO_CB(p)->flush = 0;
+ }
+
+ pp = ptype->gro_receive(&napi->gro_list, skb);
+ break;
+ }
+ rcu_read_unlock();
+
+ if (&ptype->list == head)
+ goto normal;
+
+ same_flow = NAPI_GRO_CB(skb)->same_flow;
+
+ if (pp) {
+ struct sk_buff *nskb = *pp;
+
+ *pp = nskb->next;
+ nskb->next = NULL;
+ napi_gro_complete(nskb);
+ count--;
+ }
+
+ if (same_flow)
+ goto ok;
+
+ if (NAPI_GRO_CB(skb)->flush || count >= MAX_GRO_SKBS) {
+ __skb_push(skb, -skb_network_offset(skb));
+ goto normal;
+ }
+
+ NAPI_GRO_CB(skb)->count = 1;
+ skb->next = napi->gro_list;
+ napi->gro_list = skb;
+
+ok:
+ return NET_RX_SUCCESS;
+
+normal:
+ return netif_receive_skb(skb);
+}
+EXPORT_SYMBOL(napi_gro_receive);
+
static int process_backlog(struct napi_struct *napi, int quota)
{
int work = 0;
}
local_irq_enable();
- netif_receive_skb(skb);
+ napi_gro_receive(napi, skb);
} while (++work < quota && jiffies == start_time);
+ napi_gro_flush(napi);
+
return work;
}
}
EXPORT_SYMBOL(__napi_schedule);
+void __napi_complete(struct napi_struct *n)
+{
+ BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
+ BUG_ON(n->gro_list);
+
+ list_del(&n->poll_list);
+ smp_mb__before_clear_bit();
+ clear_bit(NAPI_STATE_SCHED, &n->state);
+}
+EXPORT_SYMBOL(__napi_complete);
+
+void napi_complete(struct napi_struct *n)
+{
+ unsigned long flags;
+
+ /*
+ * don't let napi dequeue from the cpu poll list
+ * just in case its running on a different cpu
+ */
+ if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state)))
+ return;
+
+ napi_gro_flush(n);
+ local_irq_save(flags);
+ __napi_complete(n);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(napi_complete);
+
+void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
+ int (*poll)(struct napi_struct *, int), int weight)
+{
+ INIT_LIST_HEAD(&napi->poll_list);
+ napi->gro_list = NULL;
+ napi->poll = poll;
+ napi->weight = weight;
+ list_add(&napi->dev_list, &dev->napi_list);
+#ifdef CONFIG_NETPOLL
+ napi->dev = dev;
+ spin_lock_init(&napi->poll_lock);
+ napi->poll_owner = -1;
+#endif
+ set_bit(NAPI_STATE_SCHED, &napi->state);
+}
+EXPORT_SYMBOL(netif_napi_add);
+
+void netif_napi_del(struct napi_struct *napi)
+{
+ struct sk_buff *skb, *next;
+
+ list_del_init(&napi->dev_list);
+
+ for (skb = napi->gro_list; skb; skb = next) {
+ next = skb->next;
+ skb->next = NULL;
+ kfree_skb(skb);
+ }
+
+ napi->gro_list = NULL;
+}
+EXPORT_SYMBOL(netif_napi_del);
+
static void net_rx_action(struct softirq_action *h)
{
struct list_head *list = &__get_cpu_var(softnet_data).poll_list;
- unsigned long start_time = jiffies;
+ unsigned long time_limit = jiffies + 2;
int budget = netdev_budget;
void *have;
int work, weight;
/* If softirq window is exhuasted then punt.
- *
- * Note that this is a slight policy change from the
- * previous NAPI code, which would allow up to 2
- * jiffies to pass before breaking out. The test
- * used to be "jiffies - start_time > 1".
+ * Allow this to run for 2 jiffies since which will allow
+ * an average latency of 1.5/HZ.
*/
- if (unlikely(budget <= 0 || jiffies != start_time))
+ if (unlikely(budget <= 0 || time_after(jiffies, time_limit)))
goto softnet_break;
local_irq_enable();
static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
{
- struct net_device_stats *stats = dev->get_stats(dev);
+ const struct net_device_stats *stats = dev_get_stats(dev);
seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
"%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
rcu_read_unlock();
}
-static void ptype_seq_decode(struct seq_file *seq, void *sym)
-{
-#ifdef CONFIG_KALLSYMS
- unsigned long offset = 0, symsize;
- const char *symname;
- char *modname;
- char namebuf[128];
-
- symname = kallsyms_lookup((unsigned long)sym, &symsize, &offset,
- &modname, namebuf);
-
- if (symname) {
- char *delim = ":";
-
- if (!modname)
- modname = delim = "";
- seq_printf(seq, "%s%s%s%s+0x%lx", delim, modname, delim,
- symname, offset);
- return;
- }
-#endif
-
- seq_printf(seq, "[%p]", sym);
-}
-
static int ptype_seq_show(struct seq_file *seq, void *v)
{
struct packet_type *pt = v;
else
seq_printf(seq, "%04x", ntohs(pt->type));
- seq_printf(seq, " %-8s ",
- pt->dev ? pt->dev->name : "");
- ptype_seq_decode(seq, pt->func);
- seq_putc(seq, '\n');
+ seq_printf(seq, " %-8s %pF\n",
+ pt->dev ? pt->dev->name : "", pt->func);
}
return 0;
return 0;
}
+static void dev_change_rx_flags(struct net_device *dev, int flags)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags)
+ ops->ndo_change_rx_flags(dev, flags);
+}
+
static int __dev_set_promiscuity(struct net_device *dev, int inc)
{
unsigned short old_flags = dev->flags;
+ uid_t uid;
+ gid_t gid;
ASSERT_RTNL();
printk(KERN_INFO "device %s %s promiscuous mode\n",
dev->name, (dev->flags & IFF_PROMISC) ? "entered" :
"left");
- if (audit_enabled)
+ if (audit_enabled) {
+ current_uid_gid(&uid, &gid);
audit_log(current->audit_context, GFP_ATOMIC,
AUDIT_ANOM_PROMISCUOUS,
"dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u",
dev->name, (dev->flags & IFF_PROMISC),
(old_flags & IFF_PROMISC),
audit_get_loginuid(current),
- current->uid, current->gid,
+ uid, gid,
audit_get_sessionid(current));
+ }
- if (dev->change_rx_flags)
- dev->change_rx_flags(dev, IFF_PROMISC);
+ dev_change_rx_flags(dev, IFF_PROMISC);
}
return 0;
}
}
}
if (dev->flags ^ old_flags) {
- if (dev->change_rx_flags)
- dev->change_rx_flags(dev, IFF_ALLMULTI);
+ dev_change_rx_flags(dev, IFF_ALLMULTI);
dev_set_rx_mode(dev);
}
return 0;
*/
void __dev_set_rx_mode(struct net_device *dev)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
/* dev_open will call this function so the list will stay sane. */
if (!(dev->flags&IFF_UP))
return;
if (!netif_device_present(dev))
return;
- if (dev->set_rx_mode)
- dev->set_rx_mode(dev);
+ if (ops->ndo_set_rx_mode)
+ ops->ndo_set_rx_mode(dev);
else {
/* Unicast addresses changes may only happen under the rtnl,
* therefore calling __dev_set_promiscuity here is safe.
dev->uc_promisc = 0;
}
- if (dev->set_multicast_list)
- dev->set_multicast_list(dev);
+ if (ops->ndo_set_multicast_list)
+ ops->ndo_set_multicast_list(dev);
}
}
netif_addr_unlock_bh(dev);
}
+/**
+ * dev_get_flags - get flags reported to userspace
+ * @dev: device
+ *
+ * Get the combination of flag bits exported through APIs to userspace.
+ */
unsigned dev_get_flags(const struct net_device *dev)
{
unsigned flags;
return flags;
}
+/**
+ * dev_change_flags - change device settings
+ * @dev: device
+ * @flags: device state flags
+ *
+ * Change settings on device based state flags. The flags are
+ * in the userspace exported format.
+ */
int dev_change_flags(struct net_device *dev, unsigned flags)
{
int ret, changes;
* Load in the correct multicast list now the flags have changed.
*/
- if (dev->change_rx_flags && (old_flags ^ flags) & IFF_MULTICAST)
- dev->change_rx_flags(dev, IFF_MULTICAST);
+ if ((old_flags ^ flags) & IFF_MULTICAST)
+ dev_change_rx_flags(dev, IFF_MULTICAST);
dev_set_rx_mode(dev);
return ret;
}
+/**
+ * dev_set_mtu - Change maximum transfer unit
+ * @dev: device
+ * @new_mtu: new transfer unit
+ *
+ * Change the maximum transfer size of the network device.
+ */
int dev_set_mtu(struct net_device *dev, int new_mtu)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
int err;
if (new_mtu == dev->mtu)
return -ENODEV;
err = 0;
- if (dev->change_mtu)
- err = dev->change_mtu(dev, new_mtu);
+ if (ops->ndo_change_mtu)
+ err = ops->ndo_change_mtu(dev, new_mtu);
else
dev->mtu = new_mtu;
+
if (!err && dev->flags & IFF_UP)
call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
return err;
}
+/**
+ * dev_set_mac_address - Change Media Access Control Address
+ * @dev: device
+ * @sa: new address
+ *
+ * Change the hardware (MAC) address of the device
+ */
int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
int err;
- if (!dev->set_mac_address)
+ if (!ops->ndo_set_mac_address)
return -EOPNOTSUPP;
if (sa->sa_family != dev->type)
return -EINVAL;
if (!netif_device_present(dev))
return -ENODEV;
- err = dev->set_mac_address(dev, sa);
+ err = ops->ndo_set_mac_address(dev, sa);
if (!err)
call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
return err;
{
int err;
struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);
+ const struct net_device_ops *ops;
if (!dev)
return -ENODEV;
+ ops = dev->netdev_ops;
+
switch (cmd) {
case SIOCSIFFLAGS: /* Set interface flags */
return dev_change_flags(dev, ifr->ifr_flags);
return 0;
case SIOCSIFMAP:
- if (dev->set_config) {
+ if (ops->ndo_set_config) {
if (!netif_device_present(dev))
return -ENODEV;
- return dev->set_config(dev, &ifr->ifr_map);
+ return ops->ndo_set_config(dev, &ifr->ifr_map);
}
return -EOPNOTSUPP;
case SIOCADDMULTI:
- if ((!dev->set_multicast_list && !dev->set_rx_mode) ||
+ if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
return -EINVAL;
if (!netif_device_present(dev))
dev->addr_len, 1);
case SIOCDELMULTI:
- if ((!dev->set_multicast_list && !dev->set_rx_mode) ||
+ if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
return -EINVAL;
if (!netif_device_present(dev))
cmd == SIOCBRDELIF ||
cmd == SIOCWANDEV) {
err = -EOPNOTSUPP;
- if (dev->do_ioctl) {
+ if (ops->ndo_do_ioctl) {
if (netif_device_present(dev))
- err = dev->do_ioctl(dev, ifr,
- cmd);
+ err = ops->ndo_do_ioctl(dev, ifr, cmd);
else
err = -ENODEV;
}
}
/* Delayed registration/unregisteration */
-static DEFINE_SPINLOCK(net_todo_list_lock);
static LIST_HEAD(net_todo_list);
static void net_set_todo(struct net_device *dev)
{
- spin_lock(&net_todo_list_lock);
list_add_tail(&dev->todo_list, &net_todo_list);
- spin_unlock(&net_todo_list_lock);
}
static void rollback_registered(struct net_device *dev)
*/
dev_addr_discard(dev);
- if (dev->uninit)
- dev->uninit(dev);
+ if (dev->netdev_ops->ndo_uninit)
+ dev->netdev_ops->ndo_uninit(dev);
/* Notifier chain MUST detach us from master device. */
WARN_ON(dev->master);
__netdev_init_queue_locks_one(dev, &dev->rx_queue, NULL);
}
+unsigned long netdev_fix_features(unsigned long features, const char *name)
+{
+ /* Fix illegal SG+CSUM combinations. */
+ if ((features & NETIF_F_SG) &&
+ !(features & NETIF_F_ALL_CSUM)) {
+ if (name)
+ printk(KERN_NOTICE "%s: Dropping NETIF_F_SG since no "
+ "checksum feature.\n", name);
+ features &= ~NETIF_F_SG;
+ }
+
+ /* TSO requires that SG is present as well. */
+ if ((features & NETIF_F_TSO) && !(features & NETIF_F_SG)) {
+ if (name)
+ printk(KERN_NOTICE "%s: Dropping NETIF_F_TSO since no "
+ "SG feature.\n", name);
+ features &= ~NETIF_F_TSO;
+ }
+
+ if (features & NETIF_F_UFO) {
+ if (!(features & NETIF_F_GEN_CSUM)) {
+ if (name)
+ printk(KERN_ERR "%s: Dropping NETIF_F_UFO "
+ "since no NETIF_F_HW_CSUM feature.\n",
+ name);
+ features &= ~NETIF_F_UFO;
+ }
+
+ if (!(features & NETIF_F_SG)) {
+ if (name)
+ printk(KERN_ERR "%s: Dropping NETIF_F_UFO "
+ "since no NETIF_F_SG feature.\n", name);
+ features &= ~NETIF_F_UFO;
+ }
+ }
+
+ return features;
+}
+EXPORT_SYMBOL(netdev_fix_features);
+
/**
* register_netdevice - register a network device
* @dev: device to register
struct hlist_head *head;
struct hlist_node *p;
int ret;
- struct net *net;
+ struct net *net = dev_net(dev);
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
/* When net_device's are persistent, this will be fatal. */
BUG_ON(dev->reg_state != NETREG_UNINITIALIZED);
- BUG_ON(!dev_net(dev));
- net = dev_net(dev);
+ BUG_ON(!net);
spin_lock_init(&dev->addr_list_lock);
netdev_set_addr_lockdep_class(dev);
dev->iflink = -1;
+#ifdef CONFIG_COMPAT_NET_DEV_OPS
+ /* Netdevice_ops API compatiability support.
+ * This is temporary until all network devices are converted.
+ */
+ if (dev->netdev_ops) {
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ dev->init = ops->ndo_init;
+ dev->uninit = ops->ndo_uninit;
+ dev->open = ops->ndo_open;
+ dev->change_rx_flags = ops->ndo_change_rx_flags;
+ dev->set_rx_mode = ops->ndo_set_rx_mode;
+ dev->set_multicast_list = ops->ndo_set_multicast_list;
+ dev->set_mac_address = ops->ndo_set_mac_address;
+ dev->validate_addr = ops->ndo_validate_addr;
+ dev->do_ioctl = ops->ndo_do_ioctl;
+ dev->set_config = ops->ndo_set_config;
+ dev->change_mtu = ops->ndo_change_mtu;
+ dev->tx_timeout = ops->ndo_tx_timeout;
+ dev->get_stats = ops->ndo_get_stats;
+ dev->vlan_rx_register = ops->ndo_vlan_rx_register;
+ dev->vlan_rx_add_vid = ops->ndo_vlan_rx_add_vid;
+ dev->vlan_rx_kill_vid = ops->ndo_vlan_rx_kill_vid;
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ dev->poll_controller = ops->ndo_poll_controller;
+#endif
+ } else {
+ char drivername[64];
+ pr_info("%s (%s): not using net_device_ops yet\n",
+ dev->name, netdev_drivername(dev, drivername, 64));
+
+ /* This works only because net_device_ops and the
+ compatiablity structure are the same. */
+ dev->netdev_ops = (void *) &(dev->init);
+ }
+#endif
+
/* Init, if this function is available */
- if (dev->init) {
- ret = dev->init(dev);
+ if (dev->netdev_ops->ndo_init) {
+ ret = dev->netdev_ops->ndo_init(dev);
if (ret) {
if (ret > 0)
ret = -EIO;
dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM);
}
-
- /* Fix illegal SG+CSUM combinations. */
- if ((dev->features & NETIF_F_SG) &&
- !(dev->features & NETIF_F_ALL_CSUM)) {
- printk(KERN_NOTICE "%s: Dropping NETIF_F_SG since no checksum feature.\n",
- dev->name);
- dev->features &= ~NETIF_F_SG;
- }
-
- /* TSO requires that SG is present as well. */
- if ((dev->features & NETIF_F_TSO) &&
- !(dev->features & NETIF_F_SG)) {
- printk(KERN_NOTICE "%s: Dropping NETIF_F_TSO since no SG feature.\n",
- dev->name);
- dev->features &= ~NETIF_F_TSO;
- }
- if (dev->features & NETIF_F_UFO) {
- if (!(dev->features & NETIF_F_HW_CSUM)) {
- printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no "
- "NETIF_F_HW_CSUM feature.\n",
- dev->name);
- dev->features &= ~NETIF_F_UFO;
- }
- if (!(dev->features & NETIF_F_SG)) {
- printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no "
- "NETIF_F_SG feature.\n",
- dev->name);
- dev->features &= ~NETIF_F_UFO;
- }
- }
+ dev->features = netdev_fix_features(dev->features, dev->name);
/* Enable software GSO if SG is supported. */
if (dev->features & NETIF_F_SG)
return ret;
err_uninit:
- if (dev->uninit)
- dev->uninit(dev);
+ if (dev->netdev_ops->ndo_uninit)
+ dev->netdev_ops->ndo_uninit(dev);
goto out;
}
* free_netdev(y1);
* free_netdev(y2);
*
- * We are invoked by rtnl_unlock() after it drops the semaphore.
+ * We are invoked by rtnl_unlock().
* This allows us to deal with problems:
* 1) We can delete sysfs objects which invoke hotplug
* without deadlocking with linkwatch via keventd.
* 2) Since we run with the RTNL semaphore not held, we can sleep
* safely in order to wait for the netdev refcnt to drop to zero.
+ *
+ * We must not return until all unregister events added during
+ * the interval the lock was held have been completed.
*/
-static DEFINE_MUTEX(net_todo_run_mutex);
void netdev_run_todo(void)
{
struct list_head list;
- /* Need to guard against multiple cpu's getting out of order. */
- mutex_lock(&net_todo_run_mutex);
-
- /* Not safe to do outside the semaphore. We must not return
- * until all unregister events invoked by the local processor
- * have been completed (either by this todo run, or one on
- * another cpu).
- */
- if (list_empty(&net_todo_list))
- goto out;
-
/* Snapshot list, allow later requests */
- spin_lock(&net_todo_list_lock);
list_replace_init(&net_todo_list, &list);
- spin_unlock(&net_todo_list_lock);
+
+ __rtnl_unlock();
while (!list_empty(&list)) {
struct net_device *dev
/* Free network device */
kobject_put(&dev->dev.kobj);
}
-
-out:
- mutex_unlock(&net_todo_run_mutex);
}
-static struct net_device_stats *internal_stats(struct net_device *dev)
-{
- return &dev->stats;
+/**
+ * dev_get_stats - get network device statistics
+ * @dev: device to get statistics from
+ *
+ * Get network statistics from device. The device driver may provide
+ * its own method by setting dev->netdev_ops->get_stats; otherwise
+ * the internal statistics structure is used.
+ */
+const struct net_device_stats *dev_get_stats(struct net_device *dev)
+ {
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (ops->ndo_get_stats)
+ return ops->ndo_get_stats(dev);
+ else
+ return &dev->stats;
}
+EXPORT_SYMBOL(dev_get_stats);
static void netdev_init_one_queue(struct net_device *dev,
struct netdev_queue *queue,
dev->num_tx_queues = queue_count;
dev->real_num_tx_queues = queue_count;
- if (sizeof_priv) {
- dev->priv = ((char *)dev +
- ((sizeof(struct net_device) + NETDEV_ALIGN_CONST)
- & ~NETDEV_ALIGN_CONST));
- }
-
dev->gso_max_size = GSO_MAX_SIZE;
netdev_init_queues(dev);
- dev->get_stats = internal_stats;
- netpoll_netdev_init(dev);
+ INIT_LIST_HEAD(&dev->napi_list);
setup(dev);
strcpy(dev->name, name);
return dev;
*/
void free_netdev(struct net_device *dev)
{
+ struct napi_struct *p, *n;
+
release_net(dev_net(dev));
kfree(dev->_tx);
+ list_for_each_entry_safe(p, n, &dev->napi_list, dev_list)
+ netif_napi_del(p);
+
/* Compatibility with error handling in drivers */
if (dev->reg_state == NETREG_UNINITIALIZED) {
kfree((char *)dev - dev->padded);
put_device(&dev->dev);
}
-/* Synchronize with packet receive processing. */
+/**
+ * synchronize_net - Synchronize with packet receive processing
+ *
+ * Wait for packets currently being received to be done.
+ * Does not block later packets from starting.
+ */
void synchronize_net(void)
{
might_sleep();
if (dev->features & NETIF_F_NETNS_LOCAL)
goto out;
+#ifdef CONFIG_SYSFS
+ /* Don't allow real devices to be moved when sysfs
+ * is enabled.
+ */
+ err = -EINVAL;
+ if (dev->dev.parent)
+ goto out;
+#endif
+
/* Ensure the device has been registrered */
err = -EINVAL;
if (dev->reg_state != NETREG_REGISTERED)
*/
dev_addr_discard(dev);
+ netdev_unregister_kobject(dev);
+
/* Actually switch the network namespace */
dev_net_set(dev, net);
}
/* Fixup kobjects */
- netdev_unregister_kobject(dev);
err = netdev_register_kobject(dev);
WARN_ON(err);
}
/**
- * netdev_dma_regiser - register the networking subsystem as a DMA client
+ * netdev_dma_register - register the networking subsystem as a DMA client
*/
static int __init netdev_dma_register(void)
{
#endif /* CONFIG_NET_DMA */
/**
- * netdev_compute_feature - compute conjunction of two feature sets
- * @all: first feature set
- * @one: second feature set
+ * netdev_increment_features - increment feature set by one
+ * @all: current feature set
+ * @one: new feature set
+ * @mask: mask feature set
*
* Computes a new feature set after adding a device with feature set
- * @one to the master device with current feature set @all. Returns
- * the new feature set.
+ * @one to the master device with current feature set @all. Will not
+ * enable anything that is off in @mask. Returns the new feature set.
*/
-int netdev_compute_features(unsigned long all, unsigned long one)
-{
- /* if device needs checksumming, downgrade to hw checksumming */
- if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM))
- all ^= NETIF_F_NO_CSUM | NETIF_F_HW_CSUM;
-
- /* if device can't do all checksum, downgrade to ipv4/ipv6 */
- if (all & NETIF_F_HW_CSUM && !(one & NETIF_F_HW_CSUM))
- all ^= NETIF_F_HW_CSUM
- | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
-
- if (one & NETIF_F_GSO)
- one |= NETIF_F_GSO_SOFTWARE;
- one |= NETIF_F_GSO;
+unsigned long netdev_increment_features(unsigned long all, unsigned long one,
+ unsigned long mask)
+{
+ /* If device needs checksumming, downgrade to it. */
+ if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM))
+ all ^= NETIF_F_NO_CSUM | (one & NETIF_F_ALL_CSUM);
+ else if (mask & NETIF_F_ALL_CSUM) {
+ /* If one device supports v4/v6 checksumming, set for all. */
+ if (one & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM) &&
+ !(all & NETIF_F_GEN_CSUM)) {
+ all &= ~NETIF_F_ALL_CSUM;
+ all |= one & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
+ }
- /* If even one device supports robust GSO, enable it for all. */
- if (one & NETIF_F_GSO_ROBUST)
- all |= NETIF_F_GSO_ROBUST;
+ /* If one device supports hw checksumming, set for all. */
+ if (one & NETIF_F_GEN_CSUM && !(all & NETIF_F_GEN_CSUM)) {
+ all &= ~NETIF_F_ALL_CSUM;
+ all |= NETIF_F_HW_CSUM;
+ }
+ }
- all &= one | NETIF_F_LLTX;
+ one |= NETIF_F_ALL_CSUM;
- if (!(all & NETIF_F_ALL_CSUM))
- all &= ~NETIF_F_SG;
- if (!(all & NETIF_F_SG))
- all &= ~NETIF_F_GSO_MASK;
+ one |= all & NETIF_F_ONE_FOR_ALL;
+ all &= one | NETIF_F_LLTX | NETIF_F_GSO;
+ all |= one & mask & NETIF_F_ONE_FOR_ALL;
return all;
}
-EXPORT_SYMBOL(netdev_compute_features);
+EXPORT_SYMBOL(netdev_increment_features);
static struct hlist_head *netdev_create_hash(void)
{
return -ENOMEM;
}
-char *netdev_drivername(struct net_device *dev, char *buffer, int len)
+/**
+ * netdev_drivername - network driver for the device
+ * @dev: network device
+ * @buffer: buffer for resulting name
+ * @len: size of buffer
+ *
+ * Determine network driver for device.
+ */
+char *netdev_drivername(const struct net_device *dev, char *buffer, int len)
{
- struct device_driver *driver;
- struct device *parent;
+ const struct device_driver *driver;
+ const struct device *parent;
if (len <= 0 || !buffer)
return buffer;
if (dev->features & NETIF_F_NETNS_LOCAL)
continue;
+ /* Delete virtual devices */
+ if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) {
+ dev->rtnl_link_ops->dellink(dev);
+ continue;
+ }
+
/* Push remaing network devices to init_net */
snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex);
err = dev_change_net_namespace(dev, &init_net, fb_name);
if (register_pernet_subsys(&netdev_net_ops))
goto out;
- if (register_pernet_device(&default_device_ops))
- goto out;
-
/*
* Initialise the packet receive queues.
*/
queue->backlog.poll = process_backlog;
queue->backlog.weight = weight_p;
+ queue->backlog.gro_list = NULL;
}
- netdev_dma_register();
-
dev_boot_phase = 0;
+ /* The loopback device is special if any other network devices
+ * is present in a network namespace the loopback device must
+ * be present. Since we now dynamically allocate and free the
+ * loopback device ensure this invariant is maintained by
+ * keeping the loopback device as the first device on the
+ * list of network devices. Ensuring the loopback devices
+ * is the first device that appears and the last network device
+ * that disappears.
+ */
+ if (register_pernet_device(&loopback_net_ops))
+ goto out;
+
+ if (register_pernet_device(&default_device_ops))
+ goto out;
+
+ netdev_dma_register();
+
open_softirq(NET_TX_SOFTIRQ, net_tx_action);
open_softirq(NET_RX_SOFTIRQ, net_rx_action);
EXPORT_SYMBOL(br_fdb_put_hook);
#endif
-#ifdef CONFIG_KMOD
EXPORT_SYMBOL(dev_load);
-#endif
EXPORT_PER_CPU_SYMBOL(softnet_data);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff