#include <linux/jhash.h>
#include <linux/random.h>
#include <trace/events/napi.h>
+#include <linux/pci.h>
#include "net-sysfs.h"
return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)];
}
+static inline void rps_lock(struct softnet_data *sd)
+{
+#ifdef CONFIG_RPS
+ spin_lock(&sd->input_pkt_queue.lock);
+#endif
+}
+
+static inline void rps_unlock(struct softnet_data *sd)
+{
+#ifdef CONFIG_RPS
+ spin_unlock(&sd->input_pkt_queue.lock);
+#endif
+}
+
/* Device list insertion */
static int list_netdevice(struct net_device *dev)
{
* queue in the local softnet handler.
*/
-DEFINE_PER_CPU(struct softnet_data, softnet_data);
+DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
EXPORT_PER_CPU_SYMBOL(softnet_data);
#ifdef CONFIG_LOCKDEP
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(dev_alloc_name);
-static int dev_get_valid_name(struct net *net, const char *name, char *buf,
- bool fmt)
+static int dev_get_valid_name(struct net_device *dev, const char *name, bool fmt)
{
+ struct net *net;
+
+ BUG_ON(!dev_net(dev));
+ net = dev_net(dev);
+
if (!dev_valid_name(name))
return -EINVAL;
if (fmt && strchr(name, '%'))
- return __dev_alloc_name(net, name, buf);
+ return dev_alloc_name(dev, name);
else if (__dev_get_by_name(net, name))
return -EEXIST;
- else if (buf != name)
- strlcpy(buf, name, IFNAMSIZ);
+ else if (dev->name != name)
+ strlcpy(dev->name, name, IFNAMSIZ);
return 0;
}
memcpy(oldname, dev->name, IFNAMSIZ);
- err = dev_get_valid_name(net, newname, dev->name, 1);
+ err = dev_get_valid_name(dev, newname, 1);
if (err < 0)
return err;
rollback:
- /* For now only devices in the initial network namespace
- * are in sysfs.
- */
- if (net_eq(net, &init_net)) {
- ret = device_rename(&dev->dev, dev->name);
- if (ret) {
- memcpy(dev->name, oldname, IFNAMSIZ);
- return ret;
- }
+ ret = device_rename(&dev->dev, dev->name);
+ if (ret) {
+ memcpy(dev->name, oldname, IFNAMSIZ);
+ return ret;
}
write_lock_bh(&dev_base_lock);
}
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);
int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
{
+ ASSERT_RTNL();
return raw_notifier_call_chain(&netdev_chain, val, dev);
}
}
EXPORT_SYMBOL(net_disable_timestamp);
-static inline void net_timestamp(struct sk_buff *skb)
+static inline void net_timestamp_set(struct sk_buff *skb)
{
if (atomic_read(&netstamp_needed))
__net_timestamp(skb);
skb->tstamp.tv64 = 0;
}
+static inline void net_timestamp_check(struct sk_buff *skb)
+{
+ if (!skb->tstamp.tv64 && atomic_read(&netstamp_needed))
+ __net_timestamp(skb);
+}
+
/**
* dev_forward_skb - loopback an skb to another netif
*
#ifdef CONFIG_NET_CLS_ACT
if (!(skb->tstamp.tv64 && (G_TC_FROM(skb->tc_verd) & AT_INGRESS)))
- net_timestamp(skb);
+ net_timestamp_set(skb);
#else
- net_timestamp(skb);
+ net_timestamp_set(skb);
#endif
rcu_read_lock();
local_irq_save(flags);
sd = &__get_cpu_var(softnet_data);
- q->next_sched = sd->output_queue;
- sd->output_queue = q;
+ q->next_sched = NULL;
+ *sd->output_queue_tailp = q;
+ sd->output_queue_tailp = &q->next_sched;
raise_softirq_irqoff(NET_TX_SOFTIRQ);
local_irq_restore(flags);
}
* 2. No high memory really exists on this machine.
*/
-static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
+static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
{
#ifdef CONFIG_HIGHMEM
int i;
+ if (!(dev->features & NETIF_F_HIGHDMA)) {
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
+ if (PageHighMem(skb_shinfo(skb)->frags[i].page))
+ return 1;
+ }
- if (dev->features & NETIF_F_HIGHDMA)
- return 0;
-
- for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
- if (PageHighMem(skb_shinfo(skb)->frags[i].page))
- return 1;
+ if (PCI_DMA_BUS_IS_PHYS) {
+ struct device *pdev = dev->dev.parent;
+ if (!pdev)
+ return 0;
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ dma_addr_t addr = page_to_phys(skb_shinfo(skb)->frags[i].page);
+ if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask)
+ return 1;
+ }
+ }
#endif
return 0;
}
return 0;
}
+/*
+ * Try to orphan skb early, right before transmission by the device.
+ * We cannot orphan skb if tx timestamp is requested, since
+ * drivers need to call skb_tstamp_tx() to send the timestamp.
+ */
+static inline void skb_orphan_try(struct sk_buff *skb)
+{
+ if (!skb_tx(skb)->flags)
+ skb_orphan(skb);
+}
+
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq)
{
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(skb, dev);
- if (netif_needs_gso(dev, skb)) {
- if (unlikely(dev_gso_segment(skb)))
- goto out_kfree_skb;
- if (skb->next)
- goto gso;
- }
-
/*
* If device doesnt need skb->dst, release it right now while
* its hot in this cpu cache
if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
skb_dst_drop(skb);
+ skb_orphan_try(skb);
+
+ if (netif_needs_gso(dev, skb)) {
+ if (unlikely(dev_gso_segment(skb)))
+ goto out_kfree_skb;
+ if (skb->next)
+ goto gso;
+ }
+
rc = ops->ndo_start_xmit(skb, dev);
if (rc == NETDEV_TX_OK)
txq_trans_update(txq);
- /*
- * TODO: if skb_orphan() was called by
- * dev->hard_start_xmit() (for example, the unmodified
- * igb driver does that; bnx2 doesn't), then
- * skb_tx_software_timestamp() will be unable to send
- * back the time stamp.
- *
- * How can this be prevented? Always create another
- * reference to the socket before calling
- * dev->hard_start_xmit()? Prevent that skb_orphan()
- * does anything in dev->hard_start_xmit() by clearing
- * the skb destructor before the call and restoring it
- * afterwards, then doing the skb_orphan() ourselves?
- */
return rc;
}
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)
{
if (skb->sk && skb->sk->sk_hash)
hash = skb->sk->sk_hash;
else
- hash = skb->protocol;
+ hash = (__force u16) 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 "
- "real number of TX queues is %d\n",
- dev->name, 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;
}
queue_index = skb_tx_hash(dev, skb);
if (sk) {
- struct dst_entry *dst = rcu_dereference_bh(sk->sk_dst_cache);
+ struct dst_entry *dst = rcu_dereference_check(sk->sk_dst_cache, 1);
if (dst && skb_dst(skb) == dst)
sk_tx_queue_set(sk, queue_index);
* waiting to be sent out; and the qdisc is not running -
* xmit the skb directly.
*/
+ if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE))
+ skb_dst_force(skb);
__qdisc_update_bstats(q, skb->len);
if (sch_direct_xmit(skb, q, dev, txq, root_lock))
__qdisc_run(q);
rc = NET_XMIT_SUCCESS;
} else {
+ skb_dst_force(skb);
rc = qdisc_enqueue_root(skb, q);
qdisc_run(q);
}
=======================================================================*/
int netdev_max_backlog __read_mostly = 1000;
+int netdev_tstamp_prequeue __read_mostly = 1;
int netdev_budget __read_mostly = 300;
int weight_p __read_mostly = 64; /* old backlog weight */
-DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };
+/* Called with irq disabled */
+static inline void ____napi_schedule(struct softnet_data *sd,
+ struct napi_struct *napi)
+{
+ list_add_tail(&napi->poll_list, &sd->poll_list);
+ __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+}
+
+#ifdef CONFIG_RPS
+
+/* One global table that all flow-based protocols share. */
+struct rps_sock_flow_table *rps_sock_flow_table __read_mostly;
+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,
+ 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, ihl;
+ union {
+ u32 v32;
+ u16 v16[2];
+ } ports;
+
+ 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);
+ goto done;
+ }
+ rxqueue = dev->_rx + index;
+ } else
+ rxqueue = dev->_rx;
+
+ if (!rxqueue->rps_map && !rxqueue->rps_flow_table)
+ 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 = (__force u32) ip->saddr;
+ addr2 = (__force u32) 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 = (__force u32) ip6->saddr.s6_addr32[3];
+ addr2 = (__force u32) ip6->daddr.s6_addr32[3];
+ ihl = (40 >> 2);
+ break;
+ default:
+ goto done;
+ }
+ 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.v32 = * (__force u32 *) (skb->data + (ihl * 4));
+ if (ports.v16[1] < ports.v16[0])
+ swap(ports.v16[0], ports.v16[1]);
+ break;
+ }
+ default:
+ ports.v32 = 0;
+ break;
+ }
+
+ /* get a consistent hash (same value on both flow directions) */
+ if (addr2 < addr1)
+ swap(addr1, addr2);
+ skb->rxhash = jhash_3words(addr1, addr2, ports.v32, hashrnd);
+ 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) {
+ tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
+
+ if (cpu_online(tcpu)) {
+ cpu = tcpu;
+ goto done;
+ }
+ }
+
+done:
+ return cpu;
+}
+
+/* Called from hardirq (IPI) context */
+static void rps_trigger_softirq(void *data)
+{
+ struct softnet_data *sd = data;
+
+ ____napi_schedule(sd, &sd->backlog);
+ sd->received_rps++;
+}
+
+#endif /* CONFIG_RPS */
+
+/*
+ * Check if this softnet_data structure is another cpu one
+ * If yes, queue it to our IPI list and return 1
+ * If no, return 0
+ */
+static int rps_ipi_queued(struct softnet_data *sd)
+{
+#ifdef CONFIG_RPS
+ struct softnet_data *mysd = &__get_cpu_var(softnet_data);
+
+ if (sd != mysd) {
+ sd->rps_ipi_next = mysd->rps_ipi_list;
+ mysd->rps_ipi_list = sd;
+
+ __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ return 1;
+ }
+#endif /* CONFIG_RPS */
+ return 0;
+}
+
+/*
+ * 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,
+ unsigned int *qtail)
+{
+ struct softnet_data *sd;
+ unsigned long flags;
+
+ sd = &per_cpu(softnet_data, cpu);
+
+ local_irq_save(flags);
+
+ rps_lock(sd);
+ if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) {
+ if (skb_queue_len(&sd->input_pkt_queue)) {
+enqueue:
+ __skb_queue_tail(&sd->input_pkt_queue, skb);
+ input_queue_tail_incr_save(sd, qtail);
+ rps_unlock(sd);
+ local_irq_restore(flags);
+ return NET_RX_SUCCESS;
+ }
+
+ /* Schedule NAPI for backlog device
+ * We can use non atomic operation since we own the queue lock
+ */
+ if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) {
+ if (!rps_ipi_queued(sd))
+ ____napi_schedule(sd, &sd->backlog);
+ }
+ goto enqueue;
+ }
+
+ sd->dropped++;
+ rps_unlock(sd);
+ 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 ret;
/* if netpoll wants it, pretend we never saw it */
if (netpoll_rx(skb))
return NET_RX_DROP;
- if (!skb->tstamp.tv64)
- net_timestamp(skb);
+ if (netdev_tstamp_prequeue)
+ net_timestamp_check(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);
+#ifdef CONFIG_RPS
+ {
+ struct rps_dev_flow voidflow, *rflow = &voidflow;
+ int cpu;
- __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;
- }
+ rcu_read_lock();
- napi_schedule(&queue->backlog);
- goto enqueue;
- }
+ cpu = get_rps_cpu(skb->dev, skb, &rflow);
+ if (cpu < 0)
+ cpu = smp_processor_id();
- __get_cpu_var(netdev_rx_stat).dropped++;
- local_irq_restore(flags);
+ ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
- kfree_skb(skb);
- return NET_RX_DROP;
+ rcu_read_unlock();
+ }
+#else
+ {
+ unsigned int qtail;
+ ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
+ put_cpu();
+ }
+#endif
+ return ret;
}
EXPORT_SYMBOL(netif_rx);
local_irq_disable();
head = sd->output_queue;
sd->output_queue = NULL;
+ sd->output_queue_tailp = &sd->output_queue;
local_irq_enable();
while (head) {
#endif
#if defined(CONFIG_MACVLAN) || defined(CONFIG_MACVLAN_MODULE)
-struct sk_buff *(*macvlan_handle_frame_hook)(struct sk_buff *skb) __read_mostly;
+struct sk_buff *(*macvlan_handle_frame_hook)(struct macvlan_port *p,
+ struct sk_buff *skb) __read_mostly;
EXPORT_SYMBOL_GPL(macvlan_handle_frame_hook);
static inline struct sk_buff *handle_macvlan(struct sk_buff *skb,
int *ret,
struct net_device *orig_dev)
{
- if (skb->dev->macvlan_port == NULL)
+ struct macvlan_port *port;
+
+ port = rcu_dereference(skb->dev->macvlan_port);
+ if (!port)
return skb;
if (*pt_prev) {
*ret = deliver_skb(skb, *pt_prev, orig_dev);
*pt_prev = NULL;
}
- return macvlan_handle_frame_hook(skb);
+ return macvlan_handle_frame_hook(port, skb);
}
#else
#define handle_macvlan(skb, pt_prev, ret, orig_dev) (skb)
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
+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 netif_receive_skb(struct sk_buff *skb)
+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;
struct net_device *orig_dev;
struct net_device *master;
struct net_device *null_or_orig;
- struct net_device *null_or_bond;
+ struct net_device *orig_or_bond;
int ret = NET_RX_DROP;
__be16 type;
- if (!skb->tstamp.tv64)
- net_timestamp(skb);
+ if (!netdev_tstamp_prequeue)
+ net_timestamp_check(skb);
if (vlan_tx_tag_present(skb) && vlan_hwaccel_do_receive(skb))
return NET_RX_SUCCESS;
skb->dev = master;
}
- __get_cpu_var(netdev_rx_stat).total++;
+ __get_cpu_var(softnet_data).processed++;
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
* device that may have registered for a specific ptype. The
* handler may have to adjust skb->dev and orig_dev.
*/
- null_or_bond = NULL;
+ orig_or_bond = orig_dev;
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);
+ orig_or_bond = vlan_dev_real_dev(skb->dev);
}
type = skb->protocol;
&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 ||
- ptype->dev == null_or_bond)) {
+ ptype->dev == orig_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)
+{
+ if (netdev_tstamp_prequeue)
+ net_timestamp_check(skb);
+
+#ifdef CONFIG_RPS
+ {
+ struct rps_dev_flow voidflow, *rflow = &voidflow;
+ int cpu, ret;
+
+ rcu_read_lock();
+
+ 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
+}
EXPORT_SYMBOL(netif_receive_skb);
-/* Network device is going away, flush any packets still pending */
+/* Network device is going away, flush any packets still pending
+ * Called with irqs disabled.
+ */
static void flush_backlog(void *arg)
{
struct net_device *dev = arg;
- struct softnet_data *queue = &__get_cpu_var(softnet_data);
+ struct softnet_data *sd = &__get_cpu_var(softnet_data);
struct sk_buff *skb, *tmp;
- skb_queue_walk_safe(&queue->input_pkt_queue, skb, tmp)
+ rps_lock(sd);
+ skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
+ if (skb->dev == dev) {
+ __skb_unlink(skb, &sd->input_pkt_queue);
+ kfree_skb(skb);
+ input_queue_head_incr(sd);
+ }
+ }
+ rps_unlock(sd);
+
+ skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
if (skb->dev == dev) {
- __skb_unlink(skb, &queue->input_pkt_queue);
+ __skb_unlink(skb, &sd->process_queue);
kfree_skb(skb);
+ input_queue_head_incr(sd);
}
+ }
}
static int napi_gro_complete(struct sk_buff *skb)
}
EXPORT_SYMBOL(napi_gro_frags);
-static int process_backlog(struct napi_struct *napi, int quota)
+/*
+ * net_rps_action sends any pending IPI's for rps.
+ * Note: called with local irq disabled, but exits with local irq enabled.
+ */
+static void net_rps_action_and_irq_enable(struct softnet_data *sd)
{
- int work = 0;
- struct softnet_data *queue = &__get_cpu_var(softnet_data);
- unsigned long start_time = jiffies;
+#ifdef CONFIG_RPS
+ struct softnet_data *remsd = sd->rps_ipi_list;
- napi->weight = weight_p;
- do {
- struct sk_buff *skb;
+ if (remsd) {
+ sd->rps_ipi_list = NULL;
- local_irq_disable();
- skb = __skb_dequeue(&queue->input_pkt_queue);
- if (!skb) {
- __napi_complete(napi);
- local_irq_enable();
- break;
+ local_irq_enable();
+
+ /* Send pending IPI's to kick RPS processing on remote cpus. */
+ while (remsd) {
+ struct softnet_data *next = remsd->rps_ipi_next;
+
+ if (cpu_online(remsd->cpu))
+ __smp_call_function_single(remsd->cpu,
+ &remsd->csd, 0);
+ remsd = next;
}
+ } else
+#endif
local_irq_enable();
+}
- netif_receive_skb(skb);
- } while (++work < quota && jiffies == start_time);
+static int process_backlog(struct napi_struct *napi, int quota)
+{
+ int work = 0;
+ struct softnet_data *sd = container_of(napi, struct softnet_data, backlog);
+
+#ifdef CONFIG_RPS
+ /* Check if we have pending ipi, its better to send them now,
+ * not waiting net_rx_action() end.
+ */
+ if (sd->rps_ipi_list) {
+ local_irq_disable();
+ net_rps_action_and_irq_enable(sd);
+ }
+#endif
+ napi->weight = weight_p;
+ local_irq_disable();
+ while (work < quota) {
+ struct sk_buff *skb;
+ unsigned int qlen;
+
+ while ((skb = __skb_dequeue(&sd->process_queue))) {
+ local_irq_enable();
+ __netif_receive_skb(skb);
+ local_irq_disable();
+ input_queue_head_incr(sd);
+ if (++work >= quota) {
+ local_irq_enable();
+ return work;
+ }
+ }
+
+ rps_lock(sd);
+ qlen = skb_queue_len(&sd->input_pkt_queue);
+ if (qlen)
+ skb_queue_splice_tail_init(&sd->input_pkt_queue,
+ &sd->process_queue);
+
+ if (qlen < quota - work) {
+ /*
+ * Inline a custom version of __napi_complete().
+ * only current cpu owns and manipulates this napi,
+ * and NAPI_STATE_SCHED is the only possible flag set on backlog.
+ * we can use a plain write instead of clear_bit(),
+ * and we dont need an smp_mb() memory barrier.
+ */
+ list_del(&napi->poll_list);
+ napi->state = 0;
+
+ quota = work + qlen;
+ }
+ rps_unlock(sd);
+ }
+ local_irq_enable();
return work;
}
unsigned long flags;
local_irq_save(flags);
- list_add_tail(&n->poll_list, &__get_cpu_var(softnet_data).poll_list);
- __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ ____napi_schedule(&__get_cpu_var(softnet_data), n);
local_irq_restore(flags);
}
EXPORT_SYMBOL(__napi_schedule);
}
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;
+ struct softnet_data *sd = &__get_cpu_var(softnet_data);
unsigned long time_limit = jiffies + 2;
int budget = netdev_budget;
void *have;
local_irq_disable();
- while (!list_empty(list)) {
+ while (!list_empty(&sd->poll_list)) {
struct napi_struct *n;
int work, weight;
* entries to the tail of this list, and only ->poll()
* calls can remove this head entry from the list.
*/
- n = list_first_entry(list, struct napi_struct, poll_list);
+ n = list_first_entry(&sd->poll_list, struct napi_struct, poll_list);
have = netpoll_poll_lock(n);
napi_complete(n);
local_irq_disable();
} else
- list_move_tail(&n->poll_list, list);
+ list_move_tail(&n->poll_list, &sd->poll_list);
}
netpoll_poll_unlock(have);
}
out:
- local_irq_enable();
+ net_rps_action_and_irq_enable(sd);
#ifdef CONFIG_NET_DMA
/*
return;
softnet_break:
- __get_cpu_var(netdev_rx_stat).time_squeeze++;
+ sd->time_squeeze++;
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
goto out;
}
return 0;
}
-static struct netif_rx_stats *softnet_get_online(loff_t *pos)
+static struct softnet_data *softnet_get_online(loff_t *pos)
{
- struct netif_rx_stats *rc = NULL;
+ struct softnet_data *sd = NULL;
while (*pos < nr_cpu_ids)
if (cpu_online(*pos)) {
- rc = &per_cpu(netdev_rx_stat, *pos);
+ sd = &per_cpu(softnet_data, *pos);
break;
} else
++*pos;
- return rc;
+ return sd;
}
static void *softnet_seq_start(struct seq_file *seq, loff_t *pos)
static int softnet_seq_show(struct seq_file *seq, void *v)
{
- struct netif_rx_stats *s = v;
+ struct softnet_data *sd = v;
- seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
- s->total, s->dropped, s->time_squeeze, 0,
+ seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
+ sd->processed, sd->dropped, sd->time_squeeze, 0,
0, 0, 0, 0, /* was fastroute */
- s->cpu_collision);
+ sd->cpu_collision, sd->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
netif_addr_unlock_bh(dev);
}
-/* hw addresses list handling functions */
-
-static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr,
- int addr_len, unsigned char addr_type)
-{
- struct netdev_hw_addr *ha;
- int alloc_size;
-
- if (addr_len > MAX_ADDR_LEN)
- return -EINVAL;
-
- list_for_each_entry(ha, &list->list, list) {
- if (!memcmp(ha->addr, addr, addr_len) &&
- ha->type == addr_type) {
- ha->refcount++;
- return 0;
- }
- }
-
-
- alloc_size = sizeof(*ha);
- if (alloc_size < L1_CACHE_BYTES)
- alloc_size = L1_CACHE_BYTES;
- ha = kmalloc(alloc_size, GFP_ATOMIC);
- if (!ha)
- return -ENOMEM;
- memcpy(ha->addr, addr, addr_len);
- ha->type = addr_type;
- ha->refcount = 1;
- ha->synced = false;
- list_add_tail_rcu(&ha->list, &list->list);
- list->count++;
- return 0;
-}
-
-static void ha_rcu_free(struct rcu_head *head)
-{
- struct netdev_hw_addr *ha;
-
- ha = container_of(head, struct netdev_hw_addr, rcu_head);
- kfree(ha);
-}
-
-static int __hw_addr_del(struct netdev_hw_addr_list *list, unsigned char *addr,
- int addr_len, unsigned char addr_type)
-{
- struct netdev_hw_addr *ha;
-
- list_for_each_entry(ha, &list->list, list) {
- if (!memcmp(ha->addr, addr, addr_len) &&
- (ha->type == addr_type || !addr_type)) {
- if (--ha->refcount)
- return 0;
- list_del_rcu(&ha->list);
- call_rcu(&ha->rcu_head, ha_rcu_free);
- list->count--;
- return 0;
- }
- }
- return -ENOENT;
-}
-
-static int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list,
- struct netdev_hw_addr_list *from_list,
- int addr_len,
- unsigned char addr_type)
-{
- int err;
- struct netdev_hw_addr *ha, *ha2;
- unsigned char type;
-
- list_for_each_entry(ha, &from_list->list, list) {
- type = addr_type ? addr_type : ha->type;
- err = __hw_addr_add(to_list, ha->addr, addr_len, type);
- if (err)
- goto unroll;
- }
- return 0;
-
-unroll:
- list_for_each_entry(ha2, &from_list->list, list) {
- if (ha2 == ha)
- break;
- type = addr_type ? addr_type : ha2->type;
- __hw_addr_del(to_list, ha2->addr, addr_len, type);
- }
- return err;
-}
-
-static void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list,
- struct netdev_hw_addr_list *from_list,
- int addr_len,
- unsigned char addr_type)
-{
- struct netdev_hw_addr *ha;
- unsigned char type;
-
- list_for_each_entry(ha, &from_list->list, list) {
- type = addr_type ? addr_type : ha->type;
- __hw_addr_del(to_list, ha->addr, addr_len, addr_type);
- }
-}
-
-static int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
- struct netdev_hw_addr_list *from_list,
- int addr_len)
-{
- int err = 0;
- struct netdev_hw_addr *ha, *tmp;
-
- list_for_each_entry_safe(ha, tmp, &from_list->list, list) {
- if (!ha->synced) {
- err = __hw_addr_add(to_list, ha->addr,
- addr_len, ha->type);
- if (err)
- break;
- ha->synced = true;
- ha->refcount++;
- } else if (ha->refcount == 1) {
- __hw_addr_del(to_list, ha->addr, addr_len, ha->type);
- __hw_addr_del(from_list, ha->addr, addr_len, ha->type);
- }
- }
- return err;
-}
-
-static void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
- struct netdev_hw_addr_list *from_list,
- int addr_len)
-{
- struct netdev_hw_addr *ha, *tmp;
-
- list_for_each_entry_safe(ha, tmp, &from_list->list, list) {
- if (ha->synced) {
- __hw_addr_del(to_list, ha->addr,
- addr_len, ha->type);
- ha->synced = false;
- __hw_addr_del(from_list, ha->addr,
- addr_len, ha->type);
- }
- }
-}
-
-static void __hw_addr_flush(struct netdev_hw_addr_list *list)
-{
- struct netdev_hw_addr *ha, *tmp;
-
- list_for_each_entry_safe(ha, tmp, &list->list, list) {
- list_del_rcu(&ha->list);
- call_rcu(&ha->rcu_head, ha_rcu_free);
- }
- list->count = 0;
-}
-
-static void __hw_addr_init(struct netdev_hw_addr_list *list)
-{
- INIT_LIST_HEAD(&list->list);
- list->count = 0;
-}
-
-/* Device addresses handling functions */
-
-static void dev_addr_flush(struct net_device *dev)
-{
- /* rtnl_mutex must be held here */
-
- __hw_addr_flush(&dev->dev_addrs);
- dev->dev_addr = NULL;
-}
-
-static int dev_addr_init(struct net_device *dev)
-{
- unsigned char addr[MAX_ADDR_LEN];
- struct netdev_hw_addr *ha;
- int err;
-
- /* rtnl_mutex must be held here */
-
- __hw_addr_init(&dev->dev_addrs);
- memset(addr, 0, sizeof(addr));
- err = __hw_addr_add(&dev->dev_addrs, addr, sizeof(addr),
- NETDEV_HW_ADDR_T_LAN);
- if (!err) {
- /*
- * Get the first (previously created) address from the list
- * and set dev_addr pointer to this location.
- */
- ha = list_first_entry(&dev->dev_addrs.list,
- struct netdev_hw_addr, list);
- dev->dev_addr = ha->addr;
- }
- return err;
-}
-
-/**
- * dev_addr_add - Add a device address
- * @dev: device
- * @addr: address to add
- * @addr_type: address type
- *
- * Add a device address to the device or increase the reference count if
- * it already exists.
- *
- * The caller must hold the rtnl_mutex.
- */
-int dev_addr_add(struct net_device *dev, unsigned char *addr,
- unsigned char addr_type)
-{
- int err;
-
- ASSERT_RTNL();
-
- err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type);
- if (!err)
- call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
- return err;
-}
-EXPORT_SYMBOL(dev_addr_add);
-
-/**
- * dev_addr_del - Release a device address.
- * @dev: device
- * @addr: address to delete
- * @addr_type: address type
- *
- * Release reference to a device address and remove it from the device
- * if the reference count drops to zero.
- *
- * The caller must hold the rtnl_mutex.
- */
-int dev_addr_del(struct net_device *dev, unsigned char *addr,
- unsigned char addr_type)
-{
- int err;
- struct netdev_hw_addr *ha;
-
- ASSERT_RTNL();
-
- /*
- * We can not remove the first address from the list because
- * dev->dev_addr points to that.
- */
- ha = list_first_entry(&dev->dev_addrs.list,
- struct netdev_hw_addr, list);
- if (ha->addr == dev->dev_addr && ha->refcount == 1)
- return -ENOENT;
-
- err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len,
- addr_type);
- if (!err)
- call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
- return err;
-}
-EXPORT_SYMBOL(dev_addr_del);
-
-/**
- * dev_addr_add_multiple - Add device addresses from another device
- * @to_dev: device to which addresses will be added
- * @from_dev: device from which addresses will be added
- * @addr_type: address type - 0 means type will be used from from_dev
- *
- * Add device addresses of the one device to another.
- **
- * The caller must hold the rtnl_mutex.
- */
-int dev_addr_add_multiple(struct net_device *to_dev,
- struct net_device *from_dev,
- unsigned char addr_type)
-{
- int err;
-
- ASSERT_RTNL();
-
- if (from_dev->addr_len != to_dev->addr_len)
- return -EINVAL;
- err = __hw_addr_add_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs,
- to_dev->addr_len, addr_type);
- if (!err)
- call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev);
- return err;
-}
-EXPORT_SYMBOL(dev_addr_add_multiple);
-
-/**
- * dev_addr_del_multiple - Delete device addresses by another device
- * @to_dev: device where the addresses will be deleted
- * @from_dev: device by which addresses the addresses will be deleted
- * @addr_type: address type - 0 means type will used from from_dev
- *
- * Deletes addresses in to device by the list of addresses in from device.
- *
- * The caller must hold the rtnl_mutex.
- */
-int dev_addr_del_multiple(struct net_device *to_dev,
- struct net_device *from_dev,
- unsigned char addr_type)
-{
- ASSERT_RTNL();
-
- if (from_dev->addr_len != to_dev->addr_len)
- return -EINVAL;
- __hw_addr_del_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs,
- to_dev->addr_len, addr_type);
- call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev);
- return 0;
-}
-EXPORT_SYMBOL(dev_addr_del_multiple);
-
-/* 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;
-}
-
-/**
- * dev_unicast_delete - Release secondary unicast address.
- * @dev: device
- * @addr: address to delete
- *
- * Release reference to a secondary unicast address and remove it
- * from the device if the reference count drops to zero.
- *
- * The caller must hold the rtnl_mutex.
- */
-int dev_unicast_delete(struct net_device *dev, void *addr)
-{
- int err;
-
- ASSERT_RTNL();
-
- netif_addr_lock_bh(dev);
- err = __hw_addr_del(&dev->uc, addr, dev->addr_len,
- NETDEV_HW_ADDR_T_UNICAST);
- if (!err)
- __dev_set_rx_mode(dev);
- netif_addr_unlock_bh(dev);
- return err;
-}
-EXPORT_SYMBOL(dev_unicast_delete);
-
-/**
- * dev_unicast_add - add a secondary unicast address
- * @dev: device
- * @addr: address to add
- *
- * Add a secondary unicast address to the device or increase
- * the reference count if it already exists.
- *
- * The caller must hold the rtnl_mutex.
- */
-int dev_unicast_add(struct net_device *dev, void *addr)
-{
- int err;
-
- ASSERT_RTNL();
-
- netif_addr_lock_bh(dev);
- err = __hw_addr_add(&dev->uc, addr, dev->addr_len,
- NETDEV_HW_ADDR_T_UNICAST);
- if (!err)
- __dev_set_rx_mode(dev);
- netif_addr_unlock_bh(dev);
- return err;
-}
-EXPORT_SYMBOL(dev_unicast_add);
-
-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);
-
-/**
- * dev_unicast_sync - Synchronize device's unicast list to another device
- * @to: destination device
- * @from: source device
- *
- * Add newly added addresses to the destination device and release
- * addresses that have no users left. The source device must be
- * locked by netif_tx_lock_bh.
- *
- * This function is intended to be called from the dev->set_rx_mode
- * function of layered software devices.
- */
-int dev_unicast_sync(struct net_device *to, struct net_device *from)
-{
- int err = 0;
-
- if (to->addr_len != from->addr_len)
- return -EINVAL;
-
- netif_addr_lock_bh(to);
- err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
- if (!err)
- __dev_set_rx_mode(to);
- netif_addr_unlock_bh(to);
- return err;
-}
-EXPORT_SYMBOL(dev_unicast_sync);
-
-/**
- * dev_unicast_unsync - Remove synchronized addresses from the destination device
- * @to: destination device
- * @from: source device
- *
- * Remove all addresses that were added to the destination device by
- * dev_unicast_sync(). This function is intended to be called from the
- * dev->stop function of layered software devices.
- */
-void dev_unicast_unsync(struct net_device *to, struct net_device *from)
-{
- if (to->addr_len != from->addr_len)
- return;
-
- netif_addr_lock_bh(from);
- netif_addr_lock(to);
- __hw_addr_unsync(&to->uc, &from->uc, to->addr_len);
- __dev_set_rx_mode(to);
- netif_addr_unlock(to);
- netif_addr_unlock_bh(from);
-}
-EXPORT_SYMBOL(dev_unicast_unsync);
-
-static void dev_unicast_flush(struct net_device *dev)
-{
- netif_addr_lock_bh(dev);
- __hw_addr_flush(&dev->uc);
- netif_addr_unlock_bh(dev);
-}
-
-static void dev_unicast_init(struct net_device *dev)
-{
- __hw_addr_init(&dev->uc);
-}
-
-
-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);
- }
-}
-
-static 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);
-}
-
/**
* 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_unicast_flush(dev);
- dev_addr_discard(dev);
+ dev_uc_flush(dev);
+ dev_mc_flush(dev);
if (dev->netdev_ops->ndo_uninit)
dev->netdev_ops->ndo_uninit(dev);
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);
}
}
- ret = dev_get_valid_name(net, dev->name, dev->name, 0);
+ ret = dev_get_valid_name(dev, dev->name, 0);
if (ret)
goto err_uninit;
if (dev->features & NETIF_F_SG)
dev->features |= NETIF_F_GSO;
- netdev_initialize_kobject(dev);
-
ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
ret = notifier_to_errno(ret);
if (ret)
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_mc_init(dev);
+ dev_uc_init(dev);
dev_net_set(dev, &init_net);
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);
strcpy(dev->name, name);
return dev;
+free_rx:
+#ifdef CONFIG_RPS
+ kfree(rx);
free_tx:
+#endif
kfree(tx);
-
free_p:
kfree(p);
return NULL;
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)
/* We get here if we can't use the current device name */
if (!pat)
goto out;
- if (dev_get_valid_name(net, pat, dev->name, 1))
+ if (dev_get_valid_name(dev, pat, 1))
goto out;
}
/*
* Flush the unicast and multicast chains
*/
- dev_unicast_flush(dev);
- dev_addr_discard(dev);
-
- netdev_unregister_kobject(dev);
+ dev_uc_flush(dev);
+ dev_mc_flush(dev);
/* Actually switch the network namespace */
dev_net_set(dev, net);
}
/* Fixup kobjects */
- err = netdev_register_kobject(dev);
+ err = device_rename(&dev->dev, dev->name);
WARN_ON(err);
/* Add the device back in the hashes */
void *ocpu)
{
struct sk_buff **list_skb;
- struct Qdisc **list_net;
struct sk_buff *skb;
unsigned int cpu, oldcpu = (unsigned long)ocpu;
struct softnet_data *sd, *oldsd;
*list_skb = oldsd->completion_queue;
oldsd->completion_queue = NULL;
- /* Find end of our output_queue. */
- list_net = &sd->output_queue;
- while (*list_net)
- list_net = &(*list_net)->next_sched;
/* Append output queue from offline CPU. */
- *list_net = oldsd->output_queue;
- oldsd->output_queue = NULL;
+ if (oldsd->output_queue) {
+ *sd->output_queue_tailp = oldsd->output_queue;
+ sd->output_queue_tailp = oldsd->output_queue_tailp;
+ oldsd->output_queue = NULL;
+ oldsd->output_queue_tailp = &oldsd->output_queue;
+ }
raise_softirq_irqoff(NET_TX_SOFTIRQ);
local_irq_enable();
/* Process offline CPU's input_pkt_queue */
- while ((skb = __skb_dequeue(&oldsd->input_pkt_queue)))
+ while ((skb = __skb_dequeue(&oldsd->process_queue))) {
+ netif_rx(skb);
+ input_queue_head_incr(oldsd);
+ }
+ while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
netif_rx(skb);
+ input_queue_head_incr(oldsd);
+ }
return NOTIFY_OK;
}
*/
for_each_possible_cpu(i) {
- struct softnet_data *queue;
+ struct softnet_data *sd = &per_cpu(softnet_data, i);
- queue = &per_cpu(softnet_data, i);
- skb_queue_head_init(&queue->input_pkt_queue);
- queue->completion_queue = NULL;
- INIT_LIST_HEAD(&queue->poll_list);
+ memset(sd, 0, sizeof(*sd));
+ skb_queue_head_init(&sd->input_pkt_queue);
+ skb_queue_head_init(&sd->process_queue);
+ sd->completion_queue = NULL;
+ INIT_LIST_HEAD(&sd->poll_list);
+ sd->output_queue = NULL;
+ sd->output_queue_tailp = &sd->output_queue;
+#ifdef CONFIG_RPS
+ sd->csd.func = rps_trigger_softirq;
+ sd->csd.info = sd;
+ sd->csd.flags = 0;
+ sd->cpu = i;
+#endif
- queue->backlog.poll = process_backlog;
- queue->backlog.weight = weight_p;
- queue->backlog.gro_list = NULL;
- queue->backlog.gro_count = 0;
+ sd->backlog.poll = process_backlog;
+ sd->backlog.weight = weight_p;
+ sd->backlog.gro_list = NULL;
+ sd->backlog.gro_count = 0;
}
dev_boot_phase = 0;
static int __init initialize_hashrnd(void)
{
- get_random_bytes(&skb_tx_hashrnd, sizeof(skb_tx_hashrnd));
+ get_random_bytes(&hashrnd, sizeof(hashrnd));
return 0;
}
git.openpandora.org / pandora-kernel.git / blobdiff