#include <linux/ctype.h>
#include <linux/if_arp.h>
#include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/jhash.h>
+#include <linux/random.h>
#include "net-sysfs.h"
DEFINE_PER_CPU(struct softnet_data, softnet_data);
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#ifdef CONFIG_LOCKDEP
/*
* register_netdevice() inits txq->_xmit_lock and sets lockdep class
* according to dev->type
"_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)];
static inline unsigned short netdev_lock_pos(unsigned short dev_type)
{
return ARRAY_SIZE(netdev_lock_type) - 1;
}
-static inline void netdev_set_lockdep_class(spinlock_t *lock,
- unsigned short dev_type)
+static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
+ unsigned short dev_type)
{
int i;
lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i],
netdev_lock_name[i]);
}
+
+static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
+{
+ int i;
+
+ i = netdev_lock_pos(dev->type);
+ lockdep_set_class_and_name(&dev->addr_list_lock,
+ &netdev_addr_lock_key[i],
+ netdev_lock_name[i]);
+}
#else
-static inline void netdev_set_lockdep_class(spinlock_t *lock,
- unsigned short dev_type)
+static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
+ unsigned short dev_type)
+{
+}
+static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
{
}
#endif
}
-void __netif_schedule(struct netdev_queue *txq)
+static inline void __netif_reschedule(struct Qdisc *q)
{
- struct net_device *dev = txq->dev;
+ struct softnet_data *sd;
+ unsigned long flags;
- if (!test_and_set_bit(__LINK_STATE_SCHED, &dev->state)) {
- 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);
- txq->next_sched = sd->output_queue;
- sd->output_queue = txq;
- 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);
return 0;
}
+static u32 simple_tx_hashrnd;
+static int simple_tx_hashrnd_initialized = 0;
+
+static u16 simple_tx_hash(struct net_device *dev, struct sk_buff *skb)
+{
+ u32 addr1, addr2, ports;
+ u32 hash, ihl;
+ u8 ip_proto;
+
+ if (unlikely(!simple_tx_hashrnd_initialized)) {
+ get_random_bytes(&simple_tx_hashrnd, 4);
+ simple_tx_hashrnd_initialized = 1;
+ }
+
+ switch (skb->protocol) {
+ case __constant_htons(ETH_P_IP):
+ 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):
+ ip_proto = ipv6_hdr(skb)->nexthdr;
+ addr1 = ipv6_hdr(skb)->saddr.s6_addr32[3];
+ addr2 = ipv6_hdr(skb)->daddr.s6_addr32[3];
+ ihl = (40 >> 2);
+ break;
+ default:
+ return 0;
+ }
+
+
+ switch (ip_proto) {
+ case IPPROTO_TCP:
+ case IPPROTO_UDP:
+ case IPPROTO_DCCP:
+ case IPPROTO_ESP:
+ case IPPROTO_AH:
+ case IPPROTO_SCTP:
+ case IPPROTO_UDPLITE:
+ ports = *((u32 *) (skb_network_header(skb) + (ihl * 4)));
+ break;
+
+ default:
+ ports = 0;
+ break;
+ }
+
+ hash = jhash_3words(addr1, addr2, ports, simple_tx_hashrnd);
+
+ return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32);
+}
+
+static struct netdev_queue *dev_pick_tx(struct net_device *dev,
+ struct sk_buff *skb)
+{
+ u16 queue_index = 0;
+
+ if (dev->select_queue)
+ queue_index = dev->select_queue(dev, skb);
+ else if (dev->real_num_tx_queues > 1)
+ queue_index = simple_tx_hash(dev, skb);
+
+ skb_set_queue_mapping(skb, queue_index);
+ return netdev_get_tx_queue(dev, queue_index);
+}
+
/**
* dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
* the BH enable code must have IRQs enabled so that it will not deadlock.
* --BLG
*/
-
-static struct netdev_queue *dev_pick_tx(struct net_device *dev,
- struct sk_buff *skb)
-{
- u16 queue_index = 0;
-
- if (dev->select_queue)
- queue_index = dev->select_queue(dev, skb);
-
- skb_set_queue_mapping(skb, queue_index);
- return netdev_get_tx_queue(dev, queue_index);
-}
-
int dev_queue_xmit(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
rcu_read_lock_bh();
txq = dev_pick_tx(dev, skb);
- spin_lock_prefetch(&txq->lock);
-
- /* Updates of qdisc are serialized by queue->lock.
- * The struct Qdisc which is pointed to by qdisc is now a
- * rcu structure - it may be accessed without acquiring
- * a lock (but the structure may be stale.) The freeing of the
- * qdisc will be deferred until it's known that there are no
- * more references to it.
- *
- * If the qdisc has an enqueue function, we still need to
- * hold the queue->lock before calling it, since queue->lock
- * also serializes access to the device queue.
- */
-
q = rcu_dereference(txq->qdisc);
+
#ifdef CONFIG_NET_CLS_ACT
skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS);
#endif
if (q->enqueue) {
- /* Grab device queue */
- spin_lock(&txq->lock);
- q = txq->qdisc;
- if (q->enqueue) {
- rc = q->enqueue(skb, q);
- qdisc_run(txq);
- spin_unlock(&txq->lock);
-
- rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc;
- goto out;
+ spinlock_t *root_lock = qdisc_lock(q);
+
+ spin_lock(root_lock);
+
+ 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(&txq->lock);
+ spin_unlock(root_lock);
+
+ goto out;
}
/* The device has no queue. Common case for software devices:
if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
if (queue->input_pkt_queue.qlen) {
enqueue:
- dev_hold(skb->dev);
__skb_queue_tail(&queue->input_pkt_queue, skb);
local_irq_restore(flags);
return NET_RX_SUCCESS;
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);
struct sk_buff *skb = clist;
clist = clist->next;
- BUG_TRAP(!atomic_read(&skb->users));
+ WARN_ON(atomic_read(&skb->users));
__kfree_skb(skb);
}
}
if (sd->output_queue) {
- struct netdev_queue *head;
+ struct Qdisc *head;
local_irq_disable();
head = sd->output_queue;
local_irq_enable();
while (head) {
- struct netdev_queue *txq = head;
- struct net_device *dev = txq->dev;
- head = head->next_sched;
+ struct Qdisc *q = head;
+ spinlock_t *root_lock;
- smp_mb__before_clear_bit();
- clear_bit(__LINK_STATE_SCHED, &dev->state);
+ head = head->next_sched;
- if (spin_trylock(&txq->lock)) {
- qdisc_run(txq);
- spin_unlock(&txq->lock);
+ 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_queue(txq);
+ if (!test_bit(__QDISC_STATE_DEACTIVATED,
+ &q->state))
+ __netif_reschedule(q);
}
}
}
rxq = &dev->rx_queue;
- spin_lock(&rxq->lock);
- if ((q = rxq->qdisc) != NULL)
- result = q->enqueue(skb, q);
- spin_unlock(&rxq->lock);
+ q = rxq->qdisc;
+ if (q != &noop_qdisc) {
+ spin_lock(qdisc_lock(q));
+ if (likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
+ result = qdisc_enqueue_root(skb, q);
+ spin_unlock(qdisc_lock(q));
+ }
return result;
}
struct packet_type **pt_prev,
int *ret, struct net_device *orig_dev)
{
- if (!skb->dev->rx_queue.qdisc)
+ if (skb->dev->rx_queue.qdisc == &noop_qdisc)
goto out;
if (*pt_prev) {
{
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->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++;
#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;
return ret;
}
+/* Network device is going away, flush any packets still pending */
+static void flush_backlog(void *arg)
+{
+ struct net_device *dev = arg;
+ struct softnet_data *queue = &__get_cpu_var(softnet_data);
+ struct sk_buff *skb, *tmp;
+
+ skb_queue_walk_safe(&queue->input_pkt_queue, skb, tmp)
+ if (skb->dev == dev) {
+ __skb_unlink(skb, &queue->input_pkt_queue);
+ kfree_skb(skb);
+ }
+}
+
static int process_backlog(struct napi_struct *napi, int quota)
{
int work = 0;
napi->weight = weight_p;
do {
struct sk_buff *skb;
- struct net_device *dev;
local_irq_disable();
skb = __skb_dequeue(&queue->input_pkt_queue);
local_irq_enable();
break;
}
-
local_irq_enable();
- dev = skb->dev;
-
netif_receive_skb(skb);
-
- dev_put(dev);
} while (++work < quota && jiffies == start_time);
return work;
*/
if (!cpus_empty(net_dma.channel_mask)) {
int chan_idx;
- for_each_cpu_mask(chan_idx, net_dma.channel_mask) {
+ for_each_cpu_mask_nr(chan_idx, net_dma.channel_mask) {
struct dma_chan *chan = net_dma.channels[chan_idx];
if (chan)
dma_async_memcpy_issue_pending(chan);
dev->uninit(dev);
/* Notifier chain MUST detach us from master device. */
- BUG_TRAP(!dev->master);
+ WARN_ON(dev->master);
/* Remove entries from kobject tree */
netdev_unregister_kobject(dev);
void *_unused)
{
spin_lock_init(&dev_queue->_xmit_lock);
- netdev_set_lockdep_class(&dev_queue->_xmit_lock, dev->type);
+ netdev_set_xmit_lockdep_class(&dev_queue->_xmit_lock, dev->type);
dev_queue->xmit_lock_owner = -1;
}
net = dev_net(dev);
spin_lock_init(&dev->addr_list_lock);
+ netdev_set_addr_lockdep_class(dev);
netdev_init_queue_locks(dev);
dev->iflink = -1;
}
}
+ /* Enable software GSO if SG is supported. */
+ if (dev->features & NETIF_F_SG)
+ dev->features |= NETIF_F_GSO;
+
netdev_initialize_kobject(dev);
ret = netdev_register_kobject(dev);
if (ret)
dev->reg_state = NETREG_UNREGISTERED;
+ on_each_cpu(flush_backlog, dev, 1);
+
netdev_wait_allrefs(dev);
/* paranoia */
BUG_ON(atomic_read(&dev->refcnt));
- BUG_TRAP(!dev->ip_ptr);
- BUG_TRAP(!dev->ip6_ptr);
- BUG_TRAP(!dev->dn_ptr);
+ WARN_ON(dev->ip_ptr);
+ WARN_ON(dev->ip6_ptr);
+ WARN_ON(dev->dn_ptr);
if (dev->destructor)
dev->destructor(dev);
struct netdev_queue *queue,
void *_unused)
{
- spin_lock_init(&queue->lock);
queue->dev = dev;
}
{
netdev_init_one_queue(dev, &dev->rx_queue, NULL);
netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
+ spin_lock_init(&dev->tx_global_lock);
}
/**
{
struct netdev_queue *tx;
struct net_device *dev;
- int alloc_size;
+ size_t alloc_size;
void *p;
BUG_ON(strlen(name) >= sizeof(dev->name));
return NULL;
}
- tx = kzalloc(sizeof(struct netdev_queue) * queue_count, GFP_KERNEL);
+ tx = kcalloc(queue_count, sizeof(struct netdev_queue), GFP_KERNEL);
if (!tx) {
printk(KERN_ERR "alloc_netdev: Unable to allocate "
"tx qdiscs.\n");
void *ocpu)
{
struct sk_buff **list_skb;
- struct netdev_queue **list_net;
+ struct Qdisc **list_net;
struct sk_buff *skb;
unsigned int cpu, oldcpu = (unsigned long)ocpu;
struct softnet_data *sd, *oldsd;
i = 0;
cpu = first_cpu(cpu_online_map);
- for_each_cpu_mask(chan_idx, net_dma->channel_mask) {
+ for_each_cpu_mask_nr(chan_idx, net_dma->channel_mask) {
chan = net_dma->channels[chan_idx];
n = ((num_online_cpus() / cpus_weight(net_dma->channel_mask))
return -ENOMEM;
}
+char *netdev_drivername(struct net_device *dev, char *buffer, int len)
+{
+ struct device_driver *driver;
+ struct device *parent;
+
+ if (len <= 0 || !buffer)
+ return buffer;
+ buffer[0] = 0;
+
+ parent = dev->dev.parent;
+
+ if (!parent)
+ return buffer;
+
+ driver = parent->driver;
+ if (driver && driver->name)
+ strlcpy(buffer, driver->name, len);
+ return buffer;
+}
+
static void __net_exit netdev_exit(struct net *net)
{
kfree(net->dev_name_head);
dev_boot_phase = 0;
- open_softirq(NET_TX_SOFTIRQ, net_tx_action, NULL);
- open_softirq(NET_RX_SOFTIRQ, net_rx_action, NULL);
+ open_softirq(NET_TX_SOFTIRQ, net_tx_action);
+ open_softirq(NET_RX_SOFTIRQ, net_rx_action);
hotcpu_notifier(dev_cpu_callback, 0);
dst_init();