diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/Makefile | 2 | ||||
-rw-r--r-- | net/core/datagram.c | 21 | ||||
-rw-r--r-- | net/core/dev.c | 1402 | ||||
-rw-r--r-- | net/core/dev_addr_lists.c | 741 | ||||
-rw-r--r-- | net/core/dev_mcast.c | 232 | ||||
-rw-r--r-- | net/core/dst.c | 45 | ||||
-rw-r--r-- | net/core/ethtool.c | 152 | ||||
-rw-r--r-- | net/core/fib_rules.c | 31 | ||||
-rw-r--r-- | net/core/filter.c | 7 | ||||
-rw-r--r-- | net/core/flow.c | 405 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 377 | ||||
-rw-r--r-- | net/core/net-sysfs.h | 1 | ||||
-rw-r--r-- | net/core/net_namespace.c | 95 | ||||
-rw-r--r-- | net/core/netpoll.c | 26 | ||||
-rw-r--r-- | net/core/pktgen.c | 58 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 369 | ||||
-rw-r--r-- | net/core/skbuff.c | 33 | ||||
-rw-r--r-- | net/core/sock.c | 78 | ||||
-rw-r--r-- | net/core/stream.c | 22 | ||||
-rw-r--r-- | net/core/sysctl_net_core.c | 75 |
20 files changed, 2731 insertions, 1441 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index 08791ac3e05..51c3eec850e 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -7,7 +7,7 @@ obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o -obj-y += dev.o ethtool.o dev_mcast.o dst.o netevent.o \ +obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o obj-$(CONFIG_XFRM) += flow.o diff --git a/net/core/datagram.c b/net/core/datagram.c index 2dccd4ee591..e0097531417 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -86,7 +86,7 @@ static int wait_for_packet(struct sock *sk, int *err, long *timeo_p) int error; DEFINE_WAIT_FUNC(wait, receiver_wake_function); - prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); /* Socket errors? */ error = sock_error(sk); @@ -115,7 +115,7 @@ static int wait_for_packet(struct sock *sk, int *err, long *timeo_p) error = 0; *timeo_p = schedule_timeout(*timeo_p); out: - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return error; interrupted: error = sock_intr_errno(*timeo_p); @@ -229,9 +229,18 @@ EXPORT_SYMBOL(skb_free_datagram); void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb) { - lock_sock(sk); - skb_free_datagram(sk, skb); - release_sock(sk); + if (likely(atomic_read(&skb->users) == 1)) + smp_rmb(); + else if (likely(!atomic_dec_and_test(&skb->users))) + return; + + lock_sock_bh(sk); + skb_orphan(skb); + sk_mem_reclaim_partial(sk); + unlock_sock_bh(sk); + + /* skb is now orphaned, can be freed outside of locked section */ + __kfree_skb(skb); } EXPORT_SYMBOL(skb_free_datagram_locked); @@ -726,7 +735,7 @@ unsigned int datagram_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; unsigned int mask; - sock_poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk_sleep(sk), wait); mask = 0; /* exceptional events? */ diff --git a/net/core/dev.c b/net/core/dev.c index f769098774b..d273e4e3ecd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -130,6 +130,7 @@ #include <linux/jhash.h> #include <linux/random.h> #include <trace/events/napi.h> +#include <linux/pci.h> #include "net-sysfs.h" @@ -207,6 +208,20 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) 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) { @@ -249,7 +264,7 @@ static RAW_NOTIFIER_HEAD(netdev_chain); * 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 @@ -773,14 +788,17 @@ EXPORT_SYMBOL(__dev_getfirstbyhwtype); 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); @@ -984,15 +1002,10 @@ int dev_change_name(struct net_device *dev, const char *newname) 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); @@ -1085,9 +1098,9 @@ void netdev_state_change(struct net_device *dev) } 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); @@ -1417,6 +1430,7 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { + ASSERT_RTNL(); return raw_notifier_call_chain(&netdev_chain, val, dev); } @@ -1435,7 +1449,7 @@ void net_disable_timestamp(void) } 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); @@ -1443,6 +1457,12 @@ static inline void net_timestamp(struct sk_buff *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 * @@ -1451,7 +1471,7 @@ static inline void net_timestamp(struct sk_buff *skb) * * return values: * NET_RX_SUCCESS (no congestion) - * NET_RX_DROP (packet was dropped) + * NET_RX_DROP (packet was dropped, but freed) * * dev_forward_skb can be used for injecting an skb from the * start_xmit function of one device into the receive queue @@ -1465,12 +1485,11 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { skb_orphan(skb); - if (!(dev->flags & IFF_UP)) - return NET_RX_DROP; - - if (skb->len > (dev->mtu + dev->hard_header_len)) + if (!(dev->flags & IFF_UP) || + (skb->len > (dev->mtu + dev->hard_header_len))) { + kfree_skb(skb); return NET_RX_DROP; - + } skb_set_dev(skb, dev); skb->tstamp.tv64 = 0; skb->pkt_type = PACKET_HOST; @@ -1490,9 +1509,9 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) #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(); @@ -1538,8 +1557,9 @@ static inline void __netif_reschedule(struct Qdisc *q) 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); } @@ -1784,18 +1804,27 @@ EXPORT_SYMBOL(netdev_rx_csum_fault); * 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; } @@ -1853,6 +1882,17 @@ static int dev_gso_segment(struct sk_buff *skb) 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) { @@ -1863,13 +1903,6 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, 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 @@ -1877,23 +1910,18 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, 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; } @@ -1932,7 +1960,7 @@ out_kfree_skb: 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) { @@ -1948,9 +1976,9 @@ 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); } @@ -1960,10 +1988,9 @@ static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) { 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; } @@ -1990,7 +2017,7 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, 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); @@ -2020,6 +2047,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, * 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); @@ -2028,6 +2057,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, rc = NET_XMIT_SUCCESS; } else { + skb_dst_force(skb); rc = qdisc_enqueue_root(skb, q); qdisc_run(q); } @@ -2175,11 +2205,249 @@ EXPORT_SYMBOL(dev_queue_xmit); =======================================================================*/ 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)) { + if (net_ratelimit()) { + 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; + } + 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); +#ifdef CONFIG_RPS + *qtail = sd->input_queue_head + + skb_queue_len(&sd->input_pkt_queue); +#endif + 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 @@ -2198,41 +2466,38 @@ DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, }; 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); @@ -2277,6 +2542,7 @@ static void net_tx_action(struct softirq_action *h) local_irq_disable(); head = sd->output_queue; sd->output_queue = NULL; + sd->output_queue_tailp = &sd->output_queue; local_irq_enable(); while (head) { @@ -2353,7 +2619,8 @@ static inline struct sk_buff *handle_bridge(struct sk_buff *skb, #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, @@ -2361,14 +2628,17 @@ 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) @@ -2469,22 +2739,56 @@ void netif_nit_deliver(struct sk_buff *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; @@ -2494,8 +2798,8 @@ int netif_receive_skb(struct sk_buff *skb) 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; @@ -2517,7 +2821,7 @@ int netif_receive_skb(struct sk_buff *skb) 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); @@ -2595,20 +2899,77 @@ out: 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, &queue->input_pkt_queue); + __skb_unlink(skb, &sd->input_pkt_queue); kfree_skb(skb); + input_queue_head_add(sd, 1); } + } + rps_unlock(sd); + + skb_queue_walk_safe(&sd->process_queue, skb, tmp) { + if (skb->dev == dev) { + __skb_unlink(skb, &sd->process_queue); + kfree_skb(skb); + } + } } static int napi_gro_complete(struct sk_buff *skb) @@ -2911,27 +3272,85 @@ gro_result_t napi_gro_frags(struct napi_struct *napi) } EXPORT_SYMBOL(napi_gro_frags); +/* + * 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) +{ +#ifdef CONFIG_RPS + struct softnet_data *remsd = sd->rps_ipi_list; + + if (remsd) { + sd->rps_ipi_list = NULL; + + 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(); +} + static int process_backlog(struct napi_struct *napi, int quota) { int work = 0; - struct softnet_data *queue = &__get_cpu_var(softnet_data); - unsigned long start_time = jiffies; + 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; - do { + local_irq_disable(); + while (work < quota) { struct sk_buff *skb; + unsigned int qlen; - local_irq_disable(); - skb = __skb_dequeue(&queue->input_pkt_queue); - if (!skb) { - __napi_complete(napi); + while ((skb = __skb_dequeue(&sd->process_queue))) { local_irq_enable(); - break; + __netif_receive_skb(skb); + if (++work >= quota) + return work; + local_irq_disable(); } - local_irq_enable(); - netif_receive_skb(skb); - } while (++work < quota && jiffies == start_time); + rps_lock(sd); + qlen = skb_queue_len(&sd->input_pkt_queue); + if (qlen) { + input_queue_head_add(sd, 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(); |