#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/hash.h>
+#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/mutex.h>
#include <linux/string.h>
{
if (unlikely(queue_index >= dev->real_num_tx_queues)) {
if (net_ratelimit()) {
- netdev_warn(dev, "selects TX queue %d, but "
- "real number of TX queues is %d\n",
- queue_index, dev->real_num_tx_queues);
+ pr_warning("%s selects TX queue %d, but "
+ "real number of TX queues is %d\n",
+ dev->name, queue_index, dev->real_num_tx_queues);
}
return 0;
}
if (dev->real_num_tx_queues > 1)
queue_index = skb_tx_hash(dev, skb);
- if (sk && sk->sk_dst_cache)
+ if (sk && rcu_dereference_check(sk->sk_dst_cache, 1))
sk_tx_queue_set(sk, queue_index);
}
}
DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };
#ifdef CONFIG_RPS
+
+/* One global table that all flow-based protocols share. */
+struct rps_sock_flow_table *rps_sock_flow_table;
+EXPORT_SYMBOL(rps_sock_flow_table);
+
/*
* 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.
+ * rcu_read_lock must be held on entry.
*/
-static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb)
+static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
+ struct rps_dev_flow **rflowp)
{
struct ipv6hdr *ip6;
struct iphdr *ip;
struct netdev_rx_queue *rxqueue;
struct rps_map *map;
+ struct rps_dev_flow_table *flow_table;
+ struct rps_sock_flow_table *sock_flow_table;
int cpu = -1;
u8 ip_proto;
+ u16 tcpu;
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);
+ pr_warning("%s received packet on queue "
+ "%u, but number of RX queues is %u\n",
+ dev->name, index, dev->num_rx_queues);
}
goto done;
}
} else
rxqueue = dev->_rx;
- if (!rxqueue->rps_map)
+ if (!rxqueue->rps_map && !rxqueue->rps_flow_table)
goto done;
if (skb->rxhash)
skb->rxhash = 1;
got_hash:
+ flow_table = rcu_dereference(rxqueue->rps_flow_table);
+ sock_flow_table = rcu_dereference(rps_sock_flow_table);
+ if (flow_table && sock_flow_table) {
+ u16 next_cpu;
+ struct rps_dev_flow *rflow;
+
+ rflow = &flow_table->flows[skb->rxhash & flow_table->mask];
+ tcpu = rflow->cpu;
+
+ next_cpu = sock_flow_table->ents[skb->rxhash &
+ sock_flow_table->mask];
+
+ /*
+ * If the desired CPU (where last recvmsg was done) is
+ * different from current CPU (one in the rx-queue flow
+ * table entry), switch if one of the following holds:
+ * - Current CPU is unset (equal to RPS_NO_CPU).
+ * - Current CPU is offline.
+ * - The current CPU's queue tail has advanced beyond the
+ * last packet that was enqueued using this table entry.
+ * This guarantees that all previous packets for the flow
+ * have been dequeued, thus preserving in order delivery.
+ */
+ if (unlikely(tcpu != next_cpu) &&
+ (tcpu == RPS_NO_CPU || !cpu_online(tcpu) ||
+ ((int)(per_cpu(softnet_data, tcpu).input_queue_head -
+ rflow->last_qtail)) >= 0)) {
+ tcpu = rflow->cpu = next_cpu;
+ if (tcpu != RPS_NO_CPU)
+ rflow->last_qtail = per_cpu(softnet_data,
+ tcpu).input_queue_head;
+ }
+ if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) {
+ *rflowp = rflow;
+ cpu = tcpu;
+ goto done;
+ }
+ }
+
map = rcu_dereference(rxqueue->rps_map);
if (map) {
- u16 tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
+ tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
if (cpu_online(tcpu)) {
cpu = tcpu;
}
done:
- rcu_read_unlock();
return cpu;
}
__napi_schedule(&queue->backlog);
__get_cpu_var(netdev_rx_stat).received_rps++;
}
-#endif /* CONFIG_SMP */
+#endif /* CONFIG_RPS */
/*
* 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)
+static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
+ unsigned int *qtail)
{
struct softnet_data *queue;
unsigned long flags;
if (queue->input_pkt_queue.qlen) {
enqueue:
__skb_queue_tail(&queue->input_pkt_queue, skb);
+#ifdef CONFIG_RPS
+ *qtail = queue->input_queue_head +
+ queue->input_pkt_queue.qlen;
+#endif
rps_unlock(queue);
local_irq_restore(flags);
return NET_RX_SUCCESS;
cpu_set(cpu, rcpus->mask[rcpus->select]);
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
- } else
- __napi_schedule(&queue->backlog);
-#else
- __napi_schedule(&queue->backlog);
+ goto enqueue;
+ }
#endif
+ __napi_schedule(&queue->backlog);
}
goto enqueue;
}
int netif_rx(struct sk_buff *skb)
{
- int cpu;
+ int ret;
/* if netpoll wants it, pretend we never saw it */
if (netpoll_rx(skb))
net_timestamp(skb);
#ifdef CONFIG_RPS
- cpu = get_rps_cpu(skb->dev, skb);
- if (cpu < 0)
- cpu = smp_processor_id();
+ {
+ struct rps_dev_flow voidflow, *rflow = &voidflow;
+ int cpu;
+
+ rcu_read_lock();
+
+ cpu = get_rps_cpu(skb->dev, skb, &rflow);
+ if (cpu < 0)
+ cpu = smp_processor_id();
+
+ ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
+
+ rcu_read_unlock();
+ }
#else
- cpu = smp_processor_id();
+ {
+ unsigned int qtail;
+ ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
+ put_cpu();
+ }
#endif
-
- return enqueue_to_backlog(skb, cpu);
+ return ret;
}
EXPORT_SYMBOL(netif_rx);
rcu_read_unlock();
}
+static inline void skb_bond_set_mac_by_master(struct sk_buff *skb,
+ struct net_device *master)
+{
+ if (skb->pkt_type == PACKET_HOST) {
+ u16 *dest = (u16 *) eth_hdr(skb)->h_dest;
+
+ memcpy(dest, master->dev_addr, ETH_ALEN);
+ }
+}
+
+/* On bonding slaves other than the currently active slave, suppress
+ * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and
+ * ARP on active-backup slaves with arp_validate enabled.
+ */
+int __skb_bond_should_drop(struct sk_buff *skb, struct net_device *master)
+{
+ struct net_device *dev = skb->dev;
+
+ if (master->priv_flags & IFF_MASTER_ARPMON)
+ dev->last_rx = jiffies;
+
+ if ((master->priv_flags & IFF_MASTER_ALB) && master->br_port) {
+ /* Do address unmangle. The local destination address
+ * will be always the one master has. Provides the right
+ * functionality in a bridge.
+ */
+ skb_bond_set_mac_by_master(skb, master);
+ }
+
+ if (dev->priv_flags & IFF_SLAVE_INACTIVE) {
+ if ((dev->priv_flags & IFF_SLAVE_NEEDARP) &&
+ skb->protocol == __cpu_to_be16(ETH_P_ARP))
+ return 0;
+
+ if (master->priv_flags & IFF_MASTER_ALB) {
+ if (skb->pkt_type != PACKET_BROADCAST &&
+ skb->pkt_type != PACKET_MULTICAST)
+ return 0;
+ }
+ if (master->priv_flags & IFF_MASTER_8023AD &&
+ skb->protocol == __cpu_to_be16(ETH_P_SLOW))
+ return 0;
+
+ return 1;
+ }
+ return 0;
+}
+EXPORT_SYMBOL(__skb_bond_should_drop);
+
static int __netif_receive_skb(struct sk_buff *skb)
{
struct packet_type *ptype, *pt_prev;
int netif_receive_skb(struct sk_buff *skb)
{
#ifdef CONFIG_RPS
- int cpu;
+ struct rps_dev_flow voidflow, *rflow = &voidflow;
+ int cpu, ret;
- cpu = get_rps_cpu(skb->dev, skb);
+ rcu_read_lock();
- if (cpu < 0)
- return __netif_receive_skb(skb);
- else
- return enqueue_to_backlog(skb, cpu);
+ cpu = get_rps_cpu(skb->dev, skb, &rflow);
+
+ if (cpu >= 0) {
+ ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
+ rcu_read_unlock();
+ } else {
+ rcu_read_unlock();
+ ret = __netif_receive_skb(skb);
+ }
+
+ return ret;
#else
return __netif_receive_skb(skb);
#endif
if (skb->dev == dev) {
__skb_unlink(skb, &queue->input_pkt_queue);
kfree_skb(skb);
+ incr_input_queue_head(queue);
}
rps_unlock(queue);
}
skb = __skb_dequeue(&queue->input_pkt_queue);
if (!skb) {
__napi_complete(napi);
- spin_unlock_irq(&queue->input_pkt_queue.lock);
+ rps_unlock(queue);
+ local_irq_enable();
break;
}
+ incr_input_queue_head(queue);
rps_unlock(queue);
local_irq_enable();
netif_addr_unlock_bh(dev);
}
-/* multicast addresses handling functions */
-
-int __dev_addr_delete(struct dev_addr_list **list, int *count,
- void *addr, int alen, int glbl)
-{
- struct dev_addr_list *da;
-
- for (; (da = *list) != NULL; list = &da->next) {
- if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 &&
- alen == da->da_addrlen) {
- if (glbl) {
- int old_glbl = da->da_gusers;
- da->da_gusers = 0;
- if (old_glbl == 0)
- break;
- }
- if (--da->da_users)
- return 0;
-
- *list = da->next;
- kfree(da);
- (*count)--;
- return 0;
- }
- }
- return -ENOENT;
-}
-
-int __dev_addr_add(struct dev_addr_list **list, int *count,
- void *addr, int alen, int glbl)
-{
- struct dev_addr_list *da;
-
- for (da = *list; da != NULL; da = da->next) {
- if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 &&
- da->da_addrlen == alen) {
- if (glbl) {
- int old_glbl = da->da_gusers;
- da->da_gusers = 1;
- if (old_glbl)
- return 0;
- }
- da->da_users++;
- return 0;
- }
- }
-
- da = kzalloc(sizeof(*da), GFP_ATOMIC);
- if (da == NULL)
- return -ENOMEM;
- memcpy(da->da_addr, addr, alen);
- da->da_addrlen = alen;
- da->da_users = 1;
- da->da_gusers = glbl ? 1 : 0;
- da->next = *list;
- *list = da;
- (*count)++;
- return 0;
-}
-
-
-int __dev_addr_sync(struct dev_addr_list **to, int *to_count,
- struct dev_addr_list **from, int *from_count)
-{
- struct dev_addr_list *da, *next;
- int err = 0;
-
- da = *from;
- while (da != NULL) {
- next = da->next;
- if (!da->da_synced) {
- err = __dev_addr_add(to, to_count,
- da->da_addr, da->da_addrlen, 0);
- if (err < 0)
- break;
- da->da_synced = 1;
- da->da_users++;
- } else if (da->da_users == 1) {
- __dev_addr_delete(to, to_count,
- da->da_addr, da->da_addrlen, 0);
- __dev_addr_delete(from, from_count,
- da->da_addr, da->da_addrlen, 0);
- }
- da = next;
- }
- return err;
-}
-EXPORT_SYMBOL_GPL(__dev_addr_sync);
-
-void __dev_addr_unsync(struct dev_addr_list **to, int *to_count,
- struct dev_addr_list **from, int *from_count)
-{
- struct dev_addr_list *da, *next;
-
- da = *from;
- while (da != NULL) {
- next = da->next;
- if (da->da_synced) {
- __dev_addr_delete(to, to_count,
- da->da_addr, da->da_addrlen, 0);
- da->da_synced = 0;
- __dev_addr_delete(from, from_count,
- da->da_addr, da->da_addrlen, 0);
- }
- da = next;
- }
-}
-EXPORT_SYMBOL_GPL(__dev_addr_unsync);
-
-static void __dev_addr_discard(struct dev_addr_list **list)
-{
- struct dev_addr_list *tmp;
-
- while (*list != NULL) {
- tmp = *list;
- *list = tmp->next;
- if (tmp->da_users > tmp->da_gusers)
- printk("__dev_addr_discard: address leakage! "
- "da_users=%d\n", tmp->da_users);
- kfree(tmp);
- }
-}
-
-void dev_addr_discard(struct net_device *dev)
-{
- netif_addr_lock_bh(dev);
-
- __dev_addr_discard(&dev->mc_list);
- netdev_mc_count(dev) = 0;
-
- netif_addr_unlock_bh(dev);
-}
-EXPORT_SYMBOL(dev_addr_discard);
-
/**
* dev_get_flags - get flags reported to userspace
* @dev: device
return -EINVAL;
if (!netif_device_present(dev))
return -ENODEV;
- return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data,
- dev->addr_len, 1);
+ return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data);
case SIOCDELMULTI:
if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
return -EINVAL;
if (!netif_device_present(dev))
return -ENODEV;
- return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data,
- dev->addr_len, 1);
+ return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data);
case SIOCSIFTXQLEN:
if (ifr->ifr_qlen < 0)
* Flush the unicast and multicast chains
*/
dev_uc_flush(dev);
- dev_addr_discard(dev);
+ dev_mc_flush(dev);
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
if (dev_addr_init(dev))
goto free_rx;
+ dev_mc_init(dev);
dev_uc_init(dev);
dev_net_set(dev, &init_net);
* Flush the unicast and multicast chains
*/
dev_uc_flush(dev);
- dev_addr_discard(dev);
+ dev_mc_flush(dev);
netdev_unregister_kobject(dev);
local_irq_enable();
/* Process offline CPU's input_pkt_queue */
- while ((skb = __skb_dequeue(&oldsd->input_pkt_queue)))
+ while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
netif_rx(skb);
+ incr_input_queue_head(oldsd);
+ }
return NOTIFY_OK;
}