skb_orphan(skb);
nf_reset(skb);
- if (!(dev->flags & IFF_UP) ||
- (skb->len > (dev->mtu + dev->hard_header_len))) {
+ if (unlikely(!(dev->flags & IFF_UP) ||
+ (skb->len > (dev->mtu + dev->hard_header_len)))) {
+ atomic_long_inc(&dev->rx_dropped);
kfree_skb(skb);
return NET_RX_DROP;
}
* Routine to help set real_num_tx_queues. To avoid skbs mapped to queues
* greater then real_num_tx_queues stale skbs on the qdisc must be flushed.
*/
-void netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
+int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
{
- unsigned int real_num = dev->real_num_tx_queues;
+ if (txq < 1 || txq > dev->num_tx_queues)
+ return -EINVAL;
+
+ if (dev->reg_state == NETREG_REGISTERED) {
+ ASSERT_RTNL();
- if (unlikely(txq > dev->num_tx_queues))
- ;
- else if (txq > real_num)
- dev->real_num_tx_queues = txq;
- else if (txq < real_num) {
- dev->real_num_tx_queues = txq;
- qdisc_reset_all_tx_gt(dev, txq);
+ if (txq < dev->real_num_tx_queues)
+ qdisc_reset_all_tx_gt(dev, txq);
}
+
+ dev->real_num_tx_queues = txq;
+ return 0;
}
EXPORT_SYMBOL(netif_set_real_num_tx_queues);
+#ifdef CONFIG_RPS
+/**
+ * netif_set_real_num_rx_queues - set actual number of RX queues used
+ * @dev: Network device
+ * @rxq: Actual number of RX queues
+ *
+ * This must be called either with the rtnl_lock held or before
+ * registration of the net device. Returns 0 on success, or a
+ * negative error code. If called before registration, it always
+ * succeeds.
+ */
+int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq)
+{
+ int rc;
+
+ if (rxq < 1 || rxq > dev->num_rx_queues)
+ return -EINVAL;
+
+ if (dev->reg_state == NETREG_REGISTERED) {
+ ASSERT_RTNL();
+
+ rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues,
+ rxq);
+ if (rc)
+ return rc;
+ }
+
+ dev->real_num_rx_queues = rxq;
+ return 0;
+}
+EXPORT_SYMBOL(netif_set_real_num_rx_queues);
+#endif
+
static inline void __netif_reschedule(struct Qdisc *q)
{
struct softnet_data *sd;
return rc;
}
+static DEFINE_PER_CPU(int, xmit_recursion);
+#define RECURSION_LIMIT 3
+
/**
* dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
if (txq->xmit_lock_owner != cpu) {
+ if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT)
+ goto recursion_alert;
+
HARD_TX_LOCK(dev, txq, cpu);
if (!netif_tx_queue_stopped(txq)) {
+ __this_cpu_inc(xmit_recursion);
rc = dev_hard_start_xmit(skb, dev, txq);
+ __this_cpu_dec(xmit_recursion);
if (dev_xmit_complete(rc)) {
HARD_TX_UNLOCK(dev, txq);
goto out;
"queue packet!\n", dev->name);
} else {
/* Recursion is detected! It is possible,
- * unfortunately */
+ * unfortunately
+ */
+recursion_alert:
if (net_ratelimit())
printk(KERN_CRIT "Dead loop on virtual device "
"%s, fix it urgently!\n", dev->name);
if (skb_rx_queue_recorded(skb)) {
u16 index = skb_get_rx_queue(skb);
- if (unlikely(index >= dev->num_rx_queues)) {
- WARN_ONCE(dev->num_rx_queues > 1, "%s received packet "
- "on queue %u, but number of RX queues is %u\n",
- dev->name, index, dev->num_rx_queues);
+ if (unlikely(index >= dev->real_num_rx_queues)) {
+ WARN_ONCE(dev->real_num_rx_queues > 1,
+ "%s received packet on queue %u, but number "
+ "of RX queues is %u\n",
+ dev->name, index, dev->real_num_rx_queues);
goto done;
}
rxqueue = dev->_rx + index;
local_irq_restore(flags);
+ atomic_long_inc(&skb->dev->rx_dropped);
kfree_skb(skb);
return NET_RX_DROP;
}
* the ingress scheduler, you just cant add policies on ingress.
*
*/
-static int ing_filter(struct sk_buff *skb)
+static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq)
{
struct net_device *dev = skb->dev;
u32 ttl = G_TC_RTTL(skb->tc_verd);
- struct netdev_queue *rxq;
int result = TC_ACT_OK;
struct Qdisc *q;
skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl);
skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
- rxq = &dev->rx_queue;
-
q = rxq->qdisc;
if (q != &noop_qdisc) {
spin_lock(qdisc_lock(q));
struct packet_type **pt_prev,
int *ret, struct net_device *orig_dev)
{
- if (skb->dev->rx_queue.qdisc == &noop_qdisc)
+ struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue);
+
+ if (!rxq || rxq->qdisc == &noop_qdisc)
goto out;
if (*pt_prev) {
*pt_prev = NULL;
}
- switch (ing_filter(skb)) {
+ switch (ing_filter(skb, rxq)) {
case TC_ACT_SHOT:
case TC_ACT_STOLEN:
kfree_skb(skb);
if (pt_prev) {
ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
} else {
+ atomic_long_inc(&skb->dev->rx_dropped);
kfree_skb(skb);
/* Jamal, now you will not able to escape explaining
* me how you were going to use this. :-)
dev = list_first_entry(head, struct net_device, unreg_list);
call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);
- synchronize_net();
+ rcu_barrier();
list_for_each_entry(dev, head, unreg_list)
dev_put(dev);
rollback_registered_many(&single);
}
-static void __netdev_init_queue_locks_one(struct net_device *dev,
- struct netdev_queue *dev_queue,
- void *_unused)
-{
- spin_lock_init(&dev_queue->_xmit_lock);
- netdev_set_xmit_lockdep_class(&dev_queue->_xmit_lock, dev->type);
- dev_queue->xmit_lock_owner = -1;
-}
-
-static void netdev_init_queue_locks(struct net_device *dev)
-{
- netdev_for_each_tx_queue(dev, __netdev_init_queue_locks_one, NULL);
- __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. */
}
EXPORT_SYMBOL(netif_stacked_transfer_operstate);
+static int netif_alloc_rx_queues(struct net_device *dev)
+{
+#ifdef CONFIG_RPS
+ unsigned int i, count = dev->num_rx_queues;
+ struct netdev_rx_queue *rx;
+
+ BUG_ON(count < 1);
+
+ rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL);
+ if (!rx) {
+ pr_err("netdev: Unable to allocate %u rx queues.\n", count);
+ return -ENOMEM;
+ }
+ dev->_rx = rx;
+
+ /*
+ * Set a pointer to first element in the array which holds the
+ * reference count.
+ */
+ for (i = 0; i < count; i++)
+ rx[i].first = rx;
+#endif
+ return 0;
+}
+
+static int netif_alloc_netdev_queues(struct net_device *dev)
+{
+ unsigned int count = dev->num_tx_queues;
+ struct netdev_queue *tx;
+
+ BUG_ON(count < 1);
+
+ tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL);
+ if (!tx) {
+ pr_err("netdev: Unable to allocate %u tx queues.\n",
+ count);
+ return -ENOMEM;
+ }
+ dev->_tx = tx;
+ return 0;
+}
+
+static void netdev_init_one_queue(struct net_device *dev,
+ struct netdev_queue *queue,
+ void *_unused)
+{
+ queue->dev = dev;
+
+ /* Initialize queue lock */
+ spin_lock_init(&queue->_xmit_lock);
+ netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type);
+ queue->xmit_lock_owner = -1;
+}
+
+static void netdev_init_queues(struct net_device *dev)
+{
+ netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
+ spin_lock_init(&dev->tx_global_lock);
+}
+
/**
* register_netdevice - register a network device
* @dev: device to register
spin_lock_init(&dev->addr_list_lock);
netdev_set_addr_lockdep_class(dev);
- netdev_init_queue_locks(dev);
dev->iflink = -1;
-#ifdef CONFIG_RPS
- if (!dev->num_rx_queues) {
- /*
- * Allocate a single RX queue if driver never called
- * alloc_netdev_mq
- */
+ ret = netif_alloc_rx_queues(dev);
+ if (ret)
+ goto out;
- dev->_rx = kzalloc(sizeof(struct netdev_rx_queue), GFP_KERNEL);
- if (!dev->_rx) {
- ret = -ENOMEM;
- goto out;
- }
+ ret = netif_alloc_netdev_queues(dev);
+ if (ret)
+ goto out;
+
+ netdev_init_queues(dev);
- dev->_rx->first = dev->_rx;
- atomic_set(&dev->_rx->count, 1);
- dev->num_rx_queues = 1;
- }
-#endif
/* Init, if this function is available */
if (dev->netdev_ops->ndo_init) {
ret = dev->netdev_ops->ndo_init(dev);
if (dev->features & NETIF_F_SG)
dev->features |= NETIF_F_GSO;
- /* Enable GRO for vlans by default if dev->features has GRO also.
- * vlan_dev_init() will do the dev->features check.
+ /* Enable GRO and NETIF_F_HIGHDMA for vlans by default,
+ * vlan_dev_init() will do the dev->features check, so these features
+ * are enabled only if supported by underlying device.
*/
- dev->vlan_features |= NETIF_F_GRO;
+ dev->vlan_features |= (NETIF_F_GRO | NETIF_F_HIGHDMA);
ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
ret = notifier_to_errno(ret);
*/
dev->reg_state = NETREG_DUMMY;
- /* initialize the ref count */
- atomic_set(&dev->refcnt, 1);
-
/* NAPI wants this */
INIT_LIST_HEAD(&dev->napi_list);
set_bit(__LINK_STATE_PRESENT, &dev->state);
set_bit(__LINK_STATE_START, &dev->state);
+ /* Note : We dont allocate pcpu_refcnt for dummy devices,
+ * because users of this 'device' dont need to change
+ * its refcount.
+ */
+
return 0;
}
EXPORT_SYMBOL_GPL(init_dummy_netdev);
}
EXPORT_SYMBOL(register_netdev);
+int netdev_refcnt_read(const struct net_device *dev)
+{
+ int i, refcnt = 0;
+
+ for_each_possible_cpu(i)
+ refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i);
+ return refcnt;
+}
+EXPORT_SYMBOL(netdev_refcnt_read);
+
/*
* netdev_wait_allrefs - wait until all references are gone.
*
static void netdev_wait_allrefs(struct net_device *dev)
{
unsigned long rebroadcast_time, warning_time;
+ int refcnt;
linkwatch_forget_dev(dev);
rebroadcast_time = warning_time = jiffies;
- while (atomic_read(&dev->refcnt) != 0) {
+ refcnt = netdev_refcnt_read(dev);
+
+ while (refcnt != 0) {
if (time_after(jiffies, rebroadcast_time + 1 * HZ)) {
rtnl_lock();
msleep(250);
+ refcnt = netdev_refcnt_read(dev);
+
if (time_after(jiffies, warning_time + 10 * HZ)) {
printk(KERN_EMERG "unregister_netdevice: "
"waiting for %s to become free. Usage "
"count = %d\n",
- dev->name, atomic_read(&dev->refcnt));
+ dev->name, refcnt);
warning_time = jiffies;
}
}
netdev_wait_allrefs(dev);
/* paranoia */
- BUG_ON(atomic_read(&dev->refcnt));
+ BUG_ON(netdev_refcnt_read(dev));
WARN_ON(rcu_dereference_raw(dev->ip_ptr));
WARN_ON(dev->ip6_ptr);
WARN_ON(dev->dn_ptr);
if (ops->ndo_get_stats64) {
memset(storage, 0, sizeof(*storage));
- return ops->ndo_get_stats64(dev, storage);
- }
- if (ops->ndo_get_stats) {
+ ops->ndo_get_stats64(dev, storage);
+ } else if (ops->ndo_get_stats) {
netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev));
- return storage;
+ } else {
+ netdev_stats_to_stats64(storage, &dev->stats);
+ dev_txq_stats_fold(dev, storage);
}
- netdev_stats_to_stats64(storage, &dev->stats);
- dev_txq_stats_fold(dev, storage);
+ storage->rx_dropped += atomic_long_read(&dev->rx_dropped);
return storage;
}
EXPORT_SYMBOL(dev_get_stats);
-static void netdev_init_one_queue(struct net_device *dev,
- struct netdev_queue *queue,
- void *_unused)
+struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
{
- queue->dev = dev;
-}
+ struct netdev_queue *queue = dev_ingress_queue(dev);
-static void netdev_init_queues(struct net_device *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);
+#ifdef CONFIG_NET_CLS_ACT
+ if (queue)
+ return queue;
+ queue = kzalloc(sizeof(*queue), GFP_KERNEL);
+ if (!queue)
+ return NULL;
+ netdev_init_one_queue(dev, queue, NULL);
+ queue->qdisc = &noop_qdisc;
+ queue->qdisc_sleeping = &noop_qdisc;
+ rcu_assign_pointer(dev->ingress_queue, queue);
+#endif
+ return queue;
}
/**
struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
void (*setup)(struct net_device *), unsigned int queue_count)
{
- struct netdev_queue *tx;
struct net_device *dev;
size_t alloc_size;
struct net_device *p;
-#ifdef CONFIG_RPS
- struct netdev_rx_queue *rx;
- int i;
-#endif
BUG_ON(strlen(name) >= sizeof(dev->name));
+ if (queue_count < 1) {
+ pr_err("alloc_netdev: Unable to allocate device "
+ "with zero queues.\n");
+ return NULL;
+ }
+
alloc_size = sizeof(struct net_device);
if (sizeof_priv) {
/* ensure 32-byte alignment of private area */
return NULL;
}
- tx = kcalloc(queue_count, sizeof(struct netdev_queue), GFP_KERNEL);
- if (!tx) {
- printk(KERN_ERR "alloc_netdev: Unable to allocate "
- "tx qdiscs.\n");
- goto free_p;
- }
-
-#ifdef CONFIG_RPS
- rx = kcalloc(queue_count, sizeof(struct netdev_rx_queue), GFP_KERNEL);
- if (!rx) {
- printk(KERN_ERR "alloc_netdev: Unable to allocate "
- "rx queues.\n");
- goto free_tx;
- }
-
- atomic_set(&rx->count, queue_count);
-
- /*
- * Set a pointer to first element in the array which holds the
- * reference count.
- */
- for (i = 0; i < queue_count; i++)
- rx[i].first = rx;
-#endif
-
dev = PTR_ALIGN(p, NETDEV_ALIGN);
dev->padded = (char *)dev - (char *)p;
+ dev->pcpu_refcnt = alloc_percpu(int);
+ if (!dev->pcpu_refcnt)
+ goto free_p;
+
if (dev_addr_init(dev))
- goto free_rx;
+ goto free_pcpu;
dev_mc_init(dev);
dev_uc_init(dev);
dev_net_set(dev, &init_net);
- dev->_tx = tx;
dev->num_tx_queues = queue_count;
dev->real_num_tx_queues = queue_count;
#ifdef CONFIG_RPS
- dev->_rx = rx;
dev->num_rx_queues = queue_count;
+ dev->real_num_rx_queues = queue_count;
#endif
dev->gso_max_size = GSO_MAX_SIZE;
- netdev_init_queues(dev);
-
INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list);
dev->ethtool_ntuple_list.count = 0;
INIT_LIST_HEAD(&dev->napi_list);
strcpy(dev->name, name);
return dev;
-free_rx:
-#ifdef CONFIG_RPS
- kfree(rx);
-free_tx:
-#endif
- kfree(tx);
+free_pcpu:
+ free_percpu(dev->pcpu_refcnt);
free_p:
kfree(p);
return NULL;
kfree(dev->_tx);
+ kfree(rcu_dereference_raw(dev->ingress_queue));
+
/* Flush device addresses */
dev_addr_flush(dev);
list_for_each_entry_safe(p, n, &dev->napi_list, dev_list)
netif_napi_del(p);
+ free_percpu(dev->pcpu_refcnt);
+ dev->pcpu_refcnt = NULL;
+
/* Compatibility with error handling in drivers */
if (dev->reg_state == NETREG_UNINITIALIZED) {
kfree((char *)dev - dev->padded);