struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
{
- struct net_device *dev;
+ struct net_device *dev, *ret = NULL;
- rtnl_lock();
- dev = __dev_getfirstbyhwtype(net, type);
- if (dev)
- dev_hold(dev);
- rtnl_unlock();
- return dev;
+ rcu_read_lock();
+ for_each_netdev_rcu(net, dev)
+ if (dev->type == type) {
+ dev_hold(dev);
+ ret = dev;
+ break;
+ }
+ rcu_read_unlock();
+ return ret;
}
EXPORT_SYMBOL(dev_getfirstbyhwtype);
}
EXPORT_SYMBOL(netdev_state_change);
-void netdev_bonding_change(struct net_device *dev, unsigned long event)
+int netdev_bonding_change(struct net_device *dev, unsigned long event)
{
- call_netdevice_notifiers(event, dev);
+ return call_netdevice_notifiers(event, dev);
}
EXPORT_SYMBOL(netdev_bonding_change);
}
EXPORT_SYMBOL(dev_load);
-/**
- * dev_open - prepare an interface for use.
- * @dev: device to open
- *
- * Takes a device from down to up state. The device's private open
- * function is invoked and then the multicast lists are loaded. Finally
- * the device is moved into the up state and a %NETDEV_UP message is
- * sent to the netdev notifier chain.
- *
- * Calling this function on an active interface is a nop. On a failure
- * a negative errno code is returned.
- */
-int dev_open(struct net_device *dev)
+static int __dev_open(struct net_device *dev)
{
const struct net_device_ops *ops = dev->netdev_ops;
int ret;
ASSERT_RTNL();
- /*
- * Is it already up?
- */
-
- if (dev->flags & IFF_UP)
- return 0;
-
/*
* Is it even present?
*/
* Wakeup transmit queue engine
*/
dev_activate(dev);
-
- /*
- * ... and announce new interface.
- */
- call_netdevice_notifiers(NETDEV_UP, dev);
}
return ret;
}
-EXPORT_SYMBOL(dev_open);
/**
- * dev_close - shutdown an interface.
- * @dev: device to shutdown
+ * dev_open - prepare an interface for use.
+ * @dev: device to open
*
- * This function moves an active device into down state. A
- * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device
- * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier
- * chain.
+ * Takes a device from down to up state. The device's private open
+ * function is invoked and then the multicast lists are loaded. Finally
+ * the device is moved into the up state and a %NETDEV_UP message is
+ * sent to the netdev notifier chain.
+ *
+ * Calling this function on an active interface is a nop. On a failure
+ * a negative errno code is returned.
*/
-int dev_close(struct net_device *dev)
+int dev_open(struct net_device *dev)
+{
+ int ret;
+
+ /*
+ * Is it already up?
+ */
+ if (dev->flags & IFF_UP)
+ return 0;
+
+ /*
+ * Open device
+ */
+ ret = __dev_open(dev);
+ if (ret < 0)
+ return ret;
+
+ /*
+ * ... and announce new interface.
+ */
+ rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING);
+ call_netdevice_notifiers(NETDEV_UP, dev);
+
+ return ret;
+}
+EXPORT_SYMBOL(dev_open);
+
+static int __dev_close(struct net_device *dev)
{
const struct net_device_ops *ops = dev->netdev_ops;
- ASSERT_RTNL();
+ ASSERT_RTNL();
might_sleep();
- if (!(dev->flags & IFF_UP))
- return 0;
-
/*
* Tell people we are going down, so that they can
* prepare to death, when device is still operating.
dev->flags &= ~IFF_UP;
/*
- * Tell people we are down
+ * Shutdown NET_DMA
*/
- call_netdevice_notifiers(NETDEV_DOWN, dev);
+ net_dmaengine_put();
+
+ return 0;
+}
+
+/**
+ * dev_close - shutdown an interface.
+ * @dev: device to shutdown
+ *
+ * This function moves an active device into down state. A
+ * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device
+ * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier
+ * chain.
+ */
+int dev_close(struct net_device *dev)
+{
+ if (!(dev->flags & IFF_UP))
+ return 0;
+
+ __dev_close(dev);
/*
- * Shutdown NET_DMA
+ * Tell people we are down
*/
- net_dmaengine_put();
+ rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING);
+ call_netdevice_notifiers(NETDEV_DOWN, dev);
return 0;
}
if (skb->len > (dev->mtu + dev->hard_header_len))
return NET_RX_DROP;
- skb_dst_drop(skb);
+ skb_set_dev(skb, dev);
skb->tstamp.tv64 = 0;
skb->pkt_type = PACKET_HOST;
skb->protocol = eth_type_trans(skb, dev);
- skb->mark = 0;
- secpath_reset(skb);
- nf_reset(skb);
return netif_rx(skb);
}
EXPORT_SYMBOL_GPL(dev_forward_skb);
return false;
}
+/**
+ * skb_dev_set -- assign a new device to a buffer
+ * @skb: buffer for the new device
+ * @dev: network device
+ *
+ * If an skb is owned by a device already, we have to reset
+ * all data private to the namespace a device belongs to
+ * before assigning it a new device.
+ */
+#ifdef CONFIG_NET_NS
+void skb_set_dev(struct sk_buff *skb, struct net_device *dev)
+{
+ skb_dst_drop(skb);
+ if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) {
+ secpath_reset(skb);
+ nf_reset(skb);
+ skb_init_secmark(skb);
+ skb->mark = 0;
+ skb->priority = 0;
+ skb->nf_trace = 0;
+ skb->ipvs_property = 0;
+#ifdef CONFIG_NET_SCHED
+ skb->tc_index = 0;
+#endif
+ }
+ skb->dev = dev;
+}
+EXPORT_SYMBOL(skb_set_dev);
+#endif /* CONFIG_NET_NS */
+
/*
* Invalidate hardware checksum when packet is to be mangled, and
* complete checksum manually on outgoing path.
skb->next = nskb->next;
nskb->next = NULL;
+
+ /*
+ * If device doesnt need nskb->dst, release it right now while
+ * its hot in this cpu cache
+ */
+ if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
+ skb_dst_drop(nskb);
+
rc = ops->ndo_start_xmit(nskb, dev);
if (unlikely(rc != NETDEV_TX_OK)) {
if (rc & ~NETDEV_TX_MASK)
return rc;
}
-static u32 skb_tx_hashrnd;
+static u32 hashrnd __read_mostly;
u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
{
else
hash = skb->protocol;
- hash = jhash_1word(hash, skb_tx_hashrnd);
+ hash = jhash_1word(hash, hashrnd);
return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32);
}
{
if (unlikely(queue_index >= dev->real_num_tx_queues)) {
if (net_ratelimit()) {
- WARN(1, "%s selects TX queue %d, but "
+ netdev_warn(dev, "selects TX queue %d, but "
"real number of TX queues is %d\n",
- dev->name, queue_index,
- dev->real_num_tx_queues);
+ queue_index, dev->real_num_tx_queues);
}
return 0;
}
return rc;
}
+/*
+ * Returns true if either:
+ * 1. skb has frag_list and the device doesn't support FRAGLIST, or
+ * 2. skb is fragmented and the device does not support SG, or if
+ * at least one of fragments is in highmem and device does not
+ * support DMA from it.
+ */
+static inline int skb_needs_linearize(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ return (skb_has_frags(skb) && !(dev->features & NETIF_F_FRAGLIST)) ||
+ (skb_shinfo(skb)->nr_frags && (!(dev->features & NETIF_F_SG) ||
+ illegal_highdma(dev, skb)));
+}
+
/**
* dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
if (netif_needs_gso(dev, skb))
goto gso;
- if (skb_has_frags(skb) &&
- !(dev->features & NETIF_F_FRAGLIST) &&
- __skb_linearize(skb))
- goto out_kfree_skb;
-
- /* Fragmented skb is linearized if device does not support SG,
- * or if at least one of fragments is in highmem and device
- * does not support DMA from it.
- */
- if (skb_shinfo(skb)->nr_frags &&
- (!(dev->features & NETIF_F_SG) || illegal_highdma(dev, skb)) &&
- __skb_linearize(skb))
+ /* Convert a paged skb to linear, if required */
+ if (skb_needs_linearize(skb, dev) && __skb_linearize(skb))
goto out_kfree_skb;
/* If packet is not checksummed and device does not support
rcu_read_lock_bh();
txq = dev_pick_tx(dev, skb);
- q = rcu_dereference(txq->qdisc);
+ q = rcu_dereference_bh(txq->qdisc);
#ifdef CONFIG_NET_CLS_ACT
skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS);
DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };
+#ifdef CONFIG_RPS
+/*
+ * get_rps_cpu is called from netif_receive_skb and returns the target
+ * CPU from the RPS map of the receiving queue for a given skb.
+ */
+static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb)
+{
+ struct ipv6hdr *ip6;
+ struct iphdr *ip;
+ struct netdev_rx_queue *rxqueue;
+ struct rps_map *map;
+ int cpu = -1;
+ u8 ip_proto;
+ u32 addr1, addr2, ports, ihl;
+
+ rcu_read_lock();
+
+ if (skb_rx_queue_recorded(skb)) {
+ u16 index = skb_get_rx_queue(skb);
+ if (unlikely(index >= dev->num_rx_queues)) {
+ if (net_ratelimit()) {
+ netdev_warn(dev, "received packet on queue "
+ "%u, but number of RX queues is %u\n",
+ index, dev->num_rx_queues);
+ }
+ goto done;
+ }
+ rxqueue = dev->_rx + index;
+ } else
+ rxqueue = dev->_rx;
+
+ if (!rxqueue->rps_map)
+ goto done;
+
+ if (skb->rxhash)
+ goto got_hash; /* Skip hash computation on packet header */
+
+ switch (skb->protocol) {
+ case __constant_htons(ETH_P_IP):
+ if (!pskb_may_pull(skb, sizeof(*ip)))
+ goto done;
+
+ ip = (struct iphdr *) skb->data;
+ ip_proto = ip->protocol;
+ addr1 = ip->saddr;
+ addr2 = ip->daddr;
+ ihl = ip->ihl;
+ break;
+ case __constant_htons(ETH_P_IPV6):
+ if (!pskb_may_pull(skb, sizeof(*ip6)))
+ goto done;
+
+ ip6 = (struct ipv6hdr *) skb->data;
+ ip_proto = ip6->nexthdr;
+ addr1 = ip6->saddr.s6_addr32[3];
+ addr2 = ip6->daddr.s6_addr32[3];
+ ihl = (40 >> 2);
+ break;
+ default:
+ goto done;
+ }
+ ports = 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:
+ if (pskb_may_pull(skb, (ihl * 4) + 4))
+ ports = *((u32 *) (skb->data + (ihl * 4)));
+ break;
+
+ default:
+ break;
+ }
+
+ skb->rxhash = jhash_3words(addr1, addr2, ports, hashrnd);
+ if (!skb->rxhash)
+ skb->rxhash = 1;
+
+got_hash:
+ map = rcu_dereference(rxqueue->rps_map);
+ if (map) {
+ u16 tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
+
+ if (cpu_online(tcpu)) {
+ cpu = tcpu;
+ goto done;
+ }
+ }
+
+done:
+ rcu_read_unlock();
+ return cpu;
+}
+
+/*
+ * This structure holds the per-CPU mask of CPUs for which IPIs are scheduled
+ * to be sent to kick remote softirq processing. There are two masks since
+ * the sending of IPIs must be done with interrupts enabled. The select field
+ * indicates the current mask that enqueue_backlog uses to schedule IPIs.
+ * select is flipped before net_rps_action is called while still under lock,
+ * net_rps_action then uses the non-selected mask to send the IPIs and clears
+ * it without conflicting with enqueue_backlog operation.
+ */
+struct rps_remote_softirq_cpus {
+ cpumask_t mask[2];
+ int select;
+};
+static DEFINE_PER_CPU(struct rps_remote_softirq_cpus, rps_remote_softirq_cpus);
+
+/* Called from hardirq (IPI) context */
+static void trigger_softirq(void *data)
+{
+ struct softnet_data *queue = data;
+ __napi_schedule(&queue->backlog);
+ __get_cpu_var(netdev_rx_stat).received_rps++;
+}
+#endif /* CONFIG_SMP */
+
+/*
+ * enqueue_to_backlog is called to queue an skb to a per CPU backlog
+ * queue (may be a remote CPU queue).
+ */
+static int enqueue_to_backlog(struct sk_buff *skb, int cpu)
+{
+ struct softnet_data *queue;
+ unsigned long flags;
+
+ queue = &per_cpu(softnet_data, cpu);
+
+ local_irq_save(flags);
+ __get_cpu_var(netdev_rx_stat).total++;
+
+ spin_lock(&queue->input_pkt_queue.lock);
+ if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
+ if (queue->input_pkt_queue.qlen) {
+enqueue:
+ __skb_queue_tail(&queue->input_pkt_queue, skb);
+ spin_unlock_irqrestore(&queue->input_pkt_queue.lock,
+ flags);
+ return NET_RX_SUCCESS;
+ }
+
+ /* Schedule NAPI for backlog device */
+ if (napi_schedule_prep(&queue->backlog)) {
+#ifdef CONFIG_RPS
+ if (cpu != smp_processor_id()) {
+ struct rps_remote_softirq_cpus *rcpus =
+ &__get_cpu_var(rps_remote_softirq_cpus);
+
+ cpu_set(cpu, rcpus->mask[rcpus->select]);
+ __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ } else
+ __napi_schedule(&queue->backlog);
+#else
+ __napi_schedule(&queue->backlog);
+#endif
+ }
+ goto enqueue;
+ }
+
+ spin_unlock(&queue->input_pkt_queue.lock);
+
+ __get_cpu_var(netdev_rx_stat).dropped++;
+ local_irq_restore(flags);
+
+ kfree_skb(skb);
+ return NET_RX_DROP;
+}
/**
* netif_rx - post buffer to the network code
int netif_rx(struct sk_buff *skb)
{
- struct softnet_data *queue;
- unsigned long flags;
+ int cpu;
/* if netpoll wants it, pretend we never saw it */
if (netpoll_rx(skb))
if (!skb->tstamp.tv64)
net_timestamp(skb);
- /*
- * The code is rearranged so that the path is the most
- * short when CPU is congested, but is still operating.
- */
- local_irq_save(flags);
- queue = &__get_cpu_var(softnet_data);
-
- __get_cpu_var(netdev_rx_stat).total++;
- if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
- if (queue->input_pkt_queue.qlen) {
-enqueue:
- __skb_queue_tail(&queue->input_pkt_queue, skb);
- local_irq_restore(flags);
- return NET_RX_SUCCESS;
- }
-
- napi_schedule(&queue->backlog);
- goto enqueue;
- }
-
- __get_cpu_var(netdev_rx_stat).dropped++;
- local_irq_restore(flags);
+#ifdef CONFIG_RPS
+ cpu = get_rps_cpu(skb->dev, skb);
+ if (cpu < 0)
+ cpu = smp_processor_id();
+#else
+ cpu = smp_processor_id();
+#endif
- kfree_skb(skb);
- return NET_RX_DROP;
+ return enqueue_to_backlog(skb, cpu);
}
EXPORT_SYMBOL(netif_rx);
rcu_read_unlock();
}
-/**
- * netif_receive_skb - process receive buffer from network
- * @skb: buffer to process
- *
- * netif_receive_skb() is the main receive data processing function.
- * It always succeeds. The buffer may be dropped during processing
- * for congestion control or by the protocol layers.
- *
- * This function may only be called from softirq context and interrupts
- * should be enabled.
- *
- * Return values (usually ignored):
- * NET_RX_SUCCESS: no congestion
- * NET_RX_DROP: packet was dropped
- */
-int netif_receive_skb(struct sk_buff *skb)
+int __netif_receive_skb(struct sk_buff *skb)
{
struct packet_type *ptype, *pt_prev;
struct net_device *orig_dev;
+ struct net_device *master;
struct net_device *null_or_orig;
+ struct net_device *null_or_bond;
int ret = NET_RX_DROP;
__be16 type;
null_or_orig = NULL;
orig_dev = skb->dev;
- if (orig_dev->master) {
- if (skb_bond_should_drop(skb))
+ master = ACCESS_ONCE(orig_dev->master);
+ if (master) {
+ if (skb_bond_should_drop(skb, master))
null_or_orig = orig_dev; /* deliver only exact match */
else
- skb->dev = orig_dev->master;
+ skb->dev = master;
}
__get_cpu_var(netdev_rx_stat).total++;
if (!skb)
goto out;
+ /*
+ * Make sure frames received on VLAN interfaces stacked on
+ * bonding interfaces still make their way to any base bonding
+ * device that may have registered for a specific ptype. The
+ * handler may have to adjust skb->dev and orig_dev.
+ */
+ null_or_bond = NULL;
+ if ((skb->dev->priv_flags & IFF_802_1Q_VLAN) &&
+ (vlan_dev_real_dev(skb->dev)->priv_flags & IFF_BONDING)) {
+ null_or_bond = vlan_dev_real_dev(skb->dev);
+ }
+
type = skb->protocol;
list_for_each_entry_rcu(ptype,
&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
- if (ptype->type == type &&
- (ptype->dev == null_or_orig || ptype->dev == skb->dev ||
- ptype->dev == orig_dev)) {
+ if (ptype->type == type && (ptype->dev == null_or_orig ||
+ ptype->dev == skb->dev || ptype->dev == orig_dev ||
+ ptype->dev == null_or_bond)) {
if (pt_prev)
ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = ptype;
rcu_read_unlock();
return ret;
}
+
+/**
+ * netif_receive_skb - process receive buffer from network
+ * @skb: buffer to process
+ *
+ * netif_receive_skb() is the main receive data processing function.
+ * It always succeeds. The buffer may be dropped during processing
+ * for congestion control or by the protocol layers.
+ *
+ * This function may only be called from softirq context and interrupts
+ * should be enabled.
+ *
+ * Return values (usually ignored):
+ * NET_RX_SUCCESS: no congestion
+ * NET_RX_DROP: packet was dropped
+ */
+int netif_receive_skb(struct sk_buff *skb)
+{
+#ifdef CONFIG_RPS
+ int cpu;
+
+ cpu = get_rps_cpu(skb->dev, skb);
+
+ if (cpu < 0)
+ return __netif_receive_skb(skb);
+ else
+ return enqueue_to_backlog(skb, cpu);
+#else
+ return __netif_receive_skb(skb);
+#endif
+}
EXPORT_SYMBOL(netif_receive_skb);
/* Network device is going away, flush any packets still pending */
-static void flush_backlog(void *arg)
+static void flush_backlog(struct net_device *dev, int cpu)
{
- struct net_device *dev = arg;
- struct softnet_data *queue = &__get_cpu_var(softnet_data);
+ struct softnet_data *queue = &per_cpu(softnet_data, cpu);
struct sk_buff *skb, *tmp;
+ unsigned long flags;
+ spin_lock_irqsave(&queue->input_pkt_queue.lock, flags);
skb_queue_walk_safe(&queue->input_pkt_queue, skb, tmp)
if (skb->dev == dev) {
__skb_unlink(skb, &queue->input_pkt_queue);
kfree_skb(skb);
}
+ spin_unlock_irqrestore(&queue->input_pkt_queue.lock, flags);
}
static int napi_gro_complete(struct sk_buff *skb)
return netif_receive_skb(skb);
}
-void napi_gro_flush(struct napi_struct *napi)
+static void napi_gro_flush(struct napi_struct *napi)
{
struct sk_buff *skb, *next;
napi->gro_count = 0;
napi->gro_list = NULL;
}
-EXPORT_SYMBOL(napi_gro_flush);
enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
do {
struct sk_buff *skb;
- local_irq_disable();
+ spin_lock_irq(&queue->input_pkt_queue.lock);
skb = __skb_dequeue(&queue->input_pkt_queue);
if (!skb) {
__napi_complete(napi);
- local_irq_enable();
+ spin_unlock_irq(&queue->input_pkt_queue.lock);
break;
}
- local_irq_enable();
+ spin_unlock_irq(&queue->input_pkt_queue.lock);
- netif_receive_skb(skb);
+ __netif_receive_skb(skb);
} while (++work < quota && jiffies == start_time);
return work;
}
EXPORT_SYMBOL(netif_napi_del);
+#ifdef CONFIG_RPS
+/*
+ * net_rps_action sends any pending IPI's for rps. This is only called from
+ * softirq and interrupts must be enabled.
+ */
+static void net_rps_action(cpumask_t *mask)
+{
+ int cpu;
+
+ /* Send pending IPI's to kick RPS processing on remote cpus. */
+ for_each_cpu_mask_nr(cpu, *mask) {
+ struct softnet_data *queue = &per_cpu(softnet_data, cpu);
+ if (cpu_online(cpu))
+ __smp_call_function_single(cpu, &queue->csd, 0);
+ }
+ cpus_clear(*mask);
+}
+#endif
static void net_rx_action(struct softirq_action *h)
{
unsigned long time_limit = jiffies + 2;
int budget = netdev_budget;
void *have;
+#ifdef CONFIG_RPS
+ int select;
+ struct rps_remote_softirq_cpus *rcpus;
+#endif
local_irq_disable();
* entries to the tail of this list, and only ->poll()
* calls can remove this head entry from the list.
*/
- n = list_entry(list->next, struct napi_struct, poll_list);
+ n = list_first_entry(list, struct napi_struct, poll_list);
have = netpoll_poll_lock(n);
netpoll_poll_unlock(have);
}
out:
+#ifdef CONFIG_RPS
+ rcpus = &__get_cpu_var(rps_remote_softirq_cpus);
+ select = rcpus->select;
+ rcpus->select ^= 1;
+
local_irq_enable();
+ net_rps_action(&rcpus->mask[select]);
+#else
+ local_irq_enable();
+#endif
+
#ifdef CONFIG_NET_DMA
/*
* There may not be any more sk_buffs coming right now, so push
{
const struct net_device_stats *stats = dev_get_stats(dev);
- seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
+ seq_printf(seq, "%6s: %7lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
"%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
dev->name, stats->rx_bytes, stats->rx_packets,
stats->rx_errors,
{
struct netif_rx_stats *s = v;
- seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
+ seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
s->total, s->dropped, s->time_squeeze, 0,
0, 0, 0, 0, /* was fastroute */
- s->cpu_collision);
+ s->cpu_collision, s->received_rps);
return 0;
}
slave->master = master;
- synchronize_net();
-
- if (old)
+ if (old) {
+ synchronize_net();
dev_put(old);
-
+ }
if (master)
slave->flags |= IFF_SLAVE;
else
/* Unicast addresses changes may only happen under the rtnl,
* therefore calling __dev_set_promiscuity here is safe.
*/
- if (dev->uc.count > 0 && !dev->uc_promisc) {
+ if (!netdev_uc_empty(dev) && !dev->uc_promisc) {
__dev_set_promiscuity(dev, 1);
dev->uc_promisc = 1;
- } else if (dev->uc.count == 0 && dev->uc_promisc) {
+ } else if (netdev_uc_empty(dev) && dev->uc_promisc) {
__dev_set_promiscuity(dev, -1);
dev->uc_promisc = 0;
}
}
EXPORT_SYMBOL(dev_unicast_unsync);
-static void dev_unicast_flush(struct net_device *dev)
+void dev_unicast_flush(struct net_device *dev)
{
netif_addr_lock_bh(dev);
__hw_addr_flush(&dev->uc);
netif_addr_unlock_bh(dev);
}
+EXPORT_SYMBOL(dev_unicast_flush);
static void dev_unicast_init(struct net_device *dev)
{
}
}
-static void dev_addr_discard(struct net_device *dev)
+void dev_addr_discard(struct net_device *dev)
{
netif_addr_lock_bh(dev);
__dev_addr_discard(&dev->mc_list);
- dev->mc_count = 0;
+ netdev_mc_count(dev) = 0;
netif_addr_unlock_bh(dev);
}
+EXPORT_SYMBOL(dev_addr_discard);
/**
* dev_get_flags - get flags reported to userspace
}
EXPORT_SYMBOL(dev_get_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 __dev_change_flags(struct net_device *dev, unsigned int flags)
{
- int ret, changes;
int old_flags = dev->flags;
+ int ret;
ASSERT_RTNL();
ret = 0;
if ((old_flags ^ flags) & IFF_UP) { /* Bit is different ? */
- ret = ((old_flags & IFF_UP) ? dev_close : dev_open)(dev);
+ ret = ((old_flags & IFF_UP) ? __dev_close : __dev_open)(dev);
if (!ret)
dev_set_rx_mode(dev);
}
- if (dev->flags & IFF_UP &&
- ((old_flags ^ dev->flags) & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI |
- IFF_VOLATILE)))
- call_netdevice_notifiers(NETDEV_CHANGE, dev);
-
if ((flags ^ dev->gflags) & IFF_PROMISC) {
int inc = (flags & IFF_PROMISC) ? 1 : -1;
dev_set_allmulti(dev, inc);
}
- /* Exclude state transition flags, already notified */
- changes = (old_flags ^ dev->flags) & ~(IFF_UP | IFF_RUNNING);
+ return ret;
+}
+
+void __dev_notify_flags(struct net_device *dev, unsigned int old_flags)
+{
+ unsigned int changes = dev->flags ^ old_flags;
+
+ if (changes & IFF_UP) {
+ if (dev->flags & IFF_UP)
+ call_netdevice_notifiers(NETDEV_UP, dev);
+ else
+ call_netdevice_notifiers(NETDEV_DOWN, dev);
+ }
+
+ if (dev->flags & IFF_UP &&
+ (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE)))
+ call_netdevice_notifiers(NETDEV_CHANGE, dev);
+}
+
+/**
+ * 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;
+ int old_flags = dev->flags;
+
+ ret = __dev_change_flags(dev, flags);
+ if (ret < 0)
+ return ret;
+
+ changes = old_flags ^ dev->flags;
if (changes)
rtmsg_ifinfo(RTM_NEWLINK, dev, changes);
+ __dev_notify_flags(dev, old_flags);
return ret;
}
EXPORT_SYMBOL(dev_change_flags);
*/
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
+ if (!dev->rtnl_link_ops ||
+ dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
+ rtmsg_ifinfo(RTM_DELLINK, dev, ~0U);
+
/*
* Flush the unicast and multicast chains
*/
}
/* Process any work delayed until the end of the batch */
- dev = list_entry(head->next, struct net_device, unreg_list);
+ dev = list_first_entry(head, struct net_device, unreg_list);
call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);
synchronize_net();
dev->iflink = -1;
+#ifdef CONFIG_RPS
+ if (!dev->num_rx_queues) {
+ /*
+ * Allocate a single RX queue if driver never called
+ * alloc_netdev_mq
+ */
+
+ dev->_rx = kzalloc(sizeof(struct netdev_rx_queue), GFP_KERNEL);
+ if (!dev->_rx) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ 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);
* Prevent userspace races by waiting until the network
* device is fully setup before sending notifications.
*/
- rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
+ if (!dev->rtnl_link_ops ||
+ dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
+ rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
out:
return ret;
while (!list_empty(&list)) {
struct net_device *dev
- = list_entry(list.next, struct net_device, todo_list);
+ = list_first_entry(&list, struct net_device, todo_list);
+ int i;
list_del(&dev->todo_list);
if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) {
dev->reg_state = NETREG_UNREGISTERED;
- on_each_cpu(flush_backlog, dev, 1);
+ for_each_online_cpu(i)
+ flush_backlog(dev, i);
netdev_wait_allrefs(dev);
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));
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;
if (dev_addr_init(dev))
- goto free_tx;
+ goto free_rx;
dev_unicast_init(dev);
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;
+#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);
INIT_LIST_HEAD(&dev->unreg_list);
INIT_LIST_HEAD(&dev->link_watch_list);
strcpy(dev->name, name);
return dev;
+free_rx:
+#ifdef CONFIG_RPS
+ kfree(rx);
free_tx:
+#endif
kfree(tx);
-
free_p:
kfree(p);
return NULL;
/* Flush device addresses */
dev_addr_flush(dev);
+ /* Clear ethtool n-tuple list */
+ ethtool_ntuple_flush(dev);
+
list_for_each_entry_safe(p, n, &dev->napi_list, dev_list)
netif_napi_del(p);
queue->completion_queue = NULL;
INIT_LIST_HEAD(&queue->poll_list);
+#ifdef CONFIG_RPS
+ queue->csd.func = trigger_softirq;
+ queue->csd.info = queue;
+ queue->csd.flags = 0;
+#endif
+
queue->backlog.poll = process_backlog;
queue->backlog.weight = weight_p;
queue->backlog.gro_list = NULL;
static int __init initialize_hashrnd(void)
{
- get_random_bytes(&skb_tx_hashrnd, sizeof(skb_tx_hashrnd));
+ get_random_bytes(&hashrnd, sizeof(hashrnd));
return 0;
}