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 | 1363 | ||||
| -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 | 318 | ||||
| -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 | 238 | ||||
| -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 |
19 files changed, 2580 insertions, 1362 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 264137fce3a..6c820650b80 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); @@ -1085,9 +1103,9 @@ 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 +1435,7 @@ 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 +1454,7 @@ 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 +1462,12 @@ 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 * @@ -1489,9 +1514,9 @@ 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(); @@ -1537,8 +1562,9 @@ 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); } @@ -1783,18 +1809,27 @@ 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; } @@ -1852,6 +1887,17 @@ 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) { @@ -1862,13 +1908,6 @@ 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 @@ -1876,23 +1915,18 @@ 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; } @@ -1931,7 +1965,7 @@ 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) { @@ -1947,9 +1981,9 @@ 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); } @@ -1959,10 +1993,9 @@ 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; } @@ -1989,7 +2022,7 @@ 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); @@ -2019,6 +2052,8 @@ 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); @@ -2027,6 +2062,7 @@ 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); } @@ -2174,11 +2210,249 @@ 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 @@ -2197,41 +2471,38 @@ 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); @@ -2276,6 +2547,7 @@ 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) { @@ -2352,7 +2624,8 @@ 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, @@ -2360,14 +2633,17 @@ 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) @@ -2468,22 +2744,56 @@ 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; @@ -2493,8 +2803,8 @@ 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; @@ -2516,7 +2826,7 @@ 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); @@ -2594,20 +2904,77 @@ 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) @@ -2910,27 +3277,85 @@ 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(); return work; } @@ -2946,8 +3371,7 @@ void __napi_schedule(struct napi_struct *n) 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); @@ -3018,17 +3442,16 @@ void netif_napi_del(struct napi_struct *napi) } 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; @@ -3046,7 +3469,7 @@ static void net_rx_action(struct softirq_action *h) * 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); @@ -3081,13 +3504,13 @@ static void net_rx_action(struct softirq_action *h) 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 /* @@ -3100,7 +3523,7 @@ out: return; softnet_break: - __get_cpu_var(netdev_rx_stat).time_squeeze++; + sd->time_squeeze++; __raise_softirq_irqoff(NET_RX_SOFTIRQ); goto out; } @@ -3301,17 +3724,17 @@ static int dev_seq_show(struct seq_file *seq, void *v) 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) @@ -3331,12 +3754,12 @@ static void softnet_seq_stop(struct seq_file *seq, void *v) 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; } @@ -3559,11 +3982,10 @@ int netdev_set_master(struct net_device *slave, struct net_device *master) slave->master = master; - synchronize_net(); - - if (old) + if (old) { + synchronize_net(); dev_put(old); - + } if (master) slave->flags |= IFF_SLAVE; else @@ -3740,562 +4162,6 @@ void dev_set_rx_mode(struct net_device *dev) 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 @@ -4606,8 +4472,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) 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) || @@ -4615,8 +4480,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) 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) @@ -4923,8 +4787,8 @@ static void rollback_registered_many(struct list_head *head) /* * 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); @@ -5073,6 +4937,24 @@ int register_netdevice(struct net_device *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); @@ -5433,6 +5315,10 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, 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)); @@ -5458,13 +5344,32 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *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); @@ -5472,6 +5377,11 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, 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); @@ -5486,9 +5396,12 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, strcpy(dev->name, name); return dev; +free_rx: +#ifdef CONFIG_RPS + kfree(rx); free_tx: +#endif kfree(tx); - free_p: kfree(p); return NULL; @@ -5690,8 +5603,8 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* * Flush the unicast and multicast chains */ - dev_unicast_flush(dev); - dev_addr_discard(dev); + dev_uc_flush(dev); + dev_mc_flush(dev); netdev_unregister_kobject(dev); @@ -5734,7 +5647,6 @@ static int dev_cpu_callback(struct notifier_block *nfb, 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; @@ -5755,19 +5667,23 @@ static int dev_cpu_callback(struct notifier_block *nfb, *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->input_pkt_queue))) { + netif_rx(skb); + input_queue_head_add(oldsd, 1); + } + while ((skb = __skb_dequeue(&oldsd->process_queue))) netif_rx(skb); return NOTIFY_OK; @@ -5984,17 +5900,26 @@ static int __init net_dev_init(void) */ 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; @@ -6029,7 +5954,7 @@ subsys_initcall(net_dev_init); static int __init initialize_hashrnd(void) { - get_random_bytes(&skb_tx_hashrnd, sizeof(skb_tx_hashrnd)); + get_random_bytes(&hashrnd, sizeof(hashrnd)); return 0; } diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c new file mode 100644 index 00000000000..508f9c18992 --- /dev/null +++ b/net/core/dev_addr_lists.c @@ -0,0 +1,741 @@ +/* + * net/core/dev_addr_lists.c - Functions for handling net device lists + * Copyright (c) 2010 Jiri Pirko <jpirko@redhat.com> + * + * This file contains functions for working with unicast, multicast and device + * addresses lists. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include <linux/list.h> +#include <linux/proc_fs.h> + +/* + * General list handling functions + */ + +static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, + unsigned char *addr, int addr_len, + unsigned char addr_type, bool global) +{ + 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) { + if (global) { + /* check if addr is already used as global */ + if (ha->global_use) + return 0; + else + ha->global_use = true; + } + 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->global_use = global; + ha->synced = false; + list_add_tail_rcu(&ha->list, &list->list); + list->count++; + return 0; +} + +static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr, + int addr_len, unsigned char addr_type) +{ + return __hw_addr_add_ex(list, addr, addr_len, addr_type, false); +} + +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_ex(struct netdev_hw_addr_list *list, + unsigned char *addr, int addr_len, + unsigned char addr_type, bool global) +{ + 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 (global) { + if (!ha->global_use) + break; + else + ha->global_use = false; + } + 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_del(struct netdev_hw_addr_list *list, unsigned char *addr, + int addr_len, unsigned char addr_type) +{ + return __hw_addr_del_ex(list, addr, addr_len, addr_type, false); +} + +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; +} +EXPORT_SYMBOL(__hw_addr_add_multiple); + +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); + } +} +EXPORT_SYMBOL(__hw_addr_del_multiple); + +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; +} +EXPORT_SYMBOL(__hw_addr_sync); + +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); + } + } +} +EXPORT_SYMBOL(__hw_addr_unsync); + +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; +} +EXPORT_SYMBOL(__hw_addr_flush); + +void __hw_addr_init(struct netdev_hw_addr_list *list) +{ + INIT_LIST_HEAD(&list->list); + list->count = 0; +} +EXPORT_SYMBOL(__hw_addr_init); + +/* + * Device addresses handling functions + */ + +/** + * dev_addr_flush - Flush device address list + * @dev: device + * + * Flush device address list and reset ->dev_addr. + * + * The caller must hold the rtnl_mutex. + */ +void dev_addr_flush(struct net_device *dev) +{ + /* rtnl_mutex must be held here */ + + __hw_addr_flush(&dev->dev_addrs); + dev->dev_addr = NULL; +} +EXPORT_SYMBOL(dev_addr_flush); + +/** + * dev_addr_init - Init device address list + * @dev: device + * + * Init device address list and create the first element, + * used by ->dev_addr. + * + * The caller must hold the rtnl_mutex. + */ +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; +} +EXPORT_SYMBOL(dev_addr_init); + +/** + * 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); + +/* + * Unicast list handling functions + */ + +/** + * dev_uc_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. + */ +int dev_uc_add(struct net_device *dev, unsigned char *addr) +{ + int err; + + 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_uc_add); + +/** + * dev_uc_del - 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. + */ +int dev_uc_del(struct net_device *dev, unsigned char *addr) +{ + int err; + + 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_uc_del); + +/** + * dev_uc_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_uc_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_uc_sync); + +/** + * dev_uc_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_uc_sync(). This function is intended to be called from the + * dev->stop function of layered software devices. + */ +void dev_uc_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_uc_unsync); + +/** + * dev_uc_flush - Flush unicast addresses + * @dev: device + * + * Flush unicast addresses. + */ +void dev_uc_flush(struct net_device *dev) +{ + netif_addr_lock_bh(dev); + __hw_addr_flush(&dev->uc); + netif_addr_unlock_bh(dev); +} +EXPORT_SYMBOL(dev_uc_flush); + +/** + * dev_uc_flush - Init unicast address list + * @dev: device + * + * Init unicast address list. + */ +void dev_uc_init(struct net_device *dev) +{ + __hw_addr_init(&dev->uc); +} +EXPORT_SYMBOL(dev_uc_init); + +/* + * Multicast list handling functions + */ + +static int __dev_mc_add(struct net_device *dev, unsigned char *addr, + bool global) +{ + int err; + + netif_addr_lock_bh(dev); + err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_MULTICAST, global); + if (!err) + __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); + return err; +} +/** + * dev_mc_add - Add a multicast address + * @dev: device + * @addr: address to add + * + * Add a multicast address to the device or increase + * the reference count if it already exists. + */ +int dev_mc_add(struct net_device *dev, unsigned char *addr) +{ + return __dev_mc_add(dev, addr, false); +} +EXPORT_SYMBOL(dev_mc_add); + +/** + * dev_mc_add_global - Add a global multicast address + * @dev: device + * @addr: address to add + * + * Add a global multicast address to the device. + */ +int dev_mc_add_global(struct net_device *dev, unsigned char *addr) +{ + return __dev_mc_add(dev, addr, true); +} +EXPORT_SYMBOL(dev_mc_add_global); + +static int __dev_mc_del(struct net_device *dev, unsigned char *addr, + bool global) +{ + int err; + + netif_addr_lock_bh(dev); + err = __hw_addr_del_ex(&dev->mc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_MULTICAST, global); + if (!err) + __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); + return err; +} + +/** + * dev_mc_del - Delete a multicast address. + * @dev: device + * @addr: address to delete + * + * Release reference to a multicast address and remove it + * from the device if the reference count drops to zero. + */ +int dev_mc_del(struct net_device *dev, unsigned char *addr) +{ + return __dev_mc_del(dev, addr, false); +} +EXPORT_SYMBOL(dev_mc_del); + +/** + * dev_mc_del_global - Delete a global multicast address. + * @dev: device + * @addr: address to delete + * + * Release reference to a multicast address and remove it + * from the device if the reference count drops to zero. + */ +int dev_mc_del_global(struct net_device *dev, unsigned char *addr) +{ + return __dev_mc_del(dev, addr, true); +} +EXPORT_SYMBOL(dev_mc_del_global); + +/** + * dev_mc_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_multicast_list + * or dev->set_rx_mode function of layered software devices. + */ +int dev_mc_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->mc, &from->mc, to->addr_len); + if (!err) + __dev_set_rx_mode(to); + netif_addr_unlock_bh(to); + return err; +} +EXPORT_SYMBOL(dev_mc_sync); + +/** + * dev_mc_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_mc_sync(). This function is intended to be called from the + * dev->stop function of layered software devices. + */ +void dev_mc_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->mc, &from->mc, to->addr_len); + __dev_set_rx_mode(to); + netif_addr_unlock(to); + netif_addr_unlock_bh(from); +} +EXPORT_SYMBOL(dev_mc_unsync); + +/** + * dev_mc_flush - Flush multicast addresses + * @dev: device + * + * Flush multicast addresses. + */ +void dev_mc_flush(struct net_device *dev) +{ + netif_addr_lock_bh(dev); + __hw_addr_flush(&dev->mc); + netif_addr_unlock_bh(dev); +} +EXPORT_SYMBOL(dev_mc_flush); + +/** + * dev_mc_flush - Init multicast address list + * @dev: device + * + * Init multicast address list. + */ +void dev_mc_init(struct net_device *dev) +{ + __hw_addr_init(&dev->mc); +} +EXPORT_SYMBOL(dev_mc_init); + +#ifdef CONFIG_PROC_FS +#include <linux/seq_file.h> + +static int dev_mc_seq_show(struct seq_file *seq, void *v) +{ + struct netdev_hw_addr *ha; + struct net_device *dev = v; + + if (v == SEQ_START_TOKEN) + return 0; + + netif_addr_lock_bh(dev); + netdev_for_each_mc_addr(ha, dev) { + int i; + + seq_printf(seq, "%-4d %-15s %-5d %-5d ", dev->ifindex, + dev->name, ha->refcount, ha->global_use); + + for (i = 0; i < dev->addr_len; i++) + seq_printf(seq, "%02x", ha->addr[i]); + + seq_putc(seq, '\n'); + } + netif_addr_unlock_bh(dev); + return 0; +} + +static const struct seq_operations dev_mc_seq_ops = { + .start = dev_seq_start, + .next = dev_seq_next, + .stop = dev_seq_stop, + .show = dev_mc_seq_show, +}; + +static int dev_mc_seq_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &dev_mc_seq_ops, + sizeof(struct seq_net_private)); +} + +static const struct file_operations dev_mc_seq_fops = { + .owner = THIS_MODULE, + .open = dev_mc_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + +#endif + +static int __net_init dev_mc_net_init(struct net *net) +{ + if (!proc_net_fops_create(net, "dev_mcast", 0, &dev_mc_seq_fops)) + return -ENOMEM; + return 0; +} + +static void __net_exit dev_mc_net_exit(struct net *net) +{ + proc_net_remove(net, "dev_mcast"); +} + +static struct pernet_operations __net_initdata dev_mc_net_ops = { + .init = dev_mc_net_init, + .exit = dev_mc_net_exit, +}; + +void __init dev_mcast_init(void) +{ + register_pernet_subsys(&dev_mc_net_ops); +} + diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c deleted file mode 100644 index 3dc295beb48..00000000000 --- a/net/core/dev_mcast.c +++ /dev/null @@ -1,232 +0,0 @@ -/* - * Linux NET3: Multicast List maintenance. - * - * Authors: - * Tim Kordas <tjk@nostromo.eeap.cwru.edu> - * Richard Underwood <richard@wuzz.demon.co.uk> - * - * Stir fried together from the IP multicast and CAP patches above - * Alan Cox <alan@lxorguk.ukuu.org.uk> - * - * Fixes: - * Alan Cox : Update the device on a real delete - * rather than any time but... - * Alan Cox : IFF_ALLMULTI support. - * Alan Cox : New format set_multicast_list() calls. - * Gleb Natapov : Remove dev_mc_lock. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/module.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> -#include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/if_ether.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/init.h> -#include <net/net_namespace.h> -#include <net/ip.h> -#include <net/route.h> -#include <linux/skbuff.h> -#include <net/sock.h> -#include <net/arp.h> - - -/* - * Device multicast list maintenance. - * - * This is used both by IP and by the user level maintenance functions. - * Unlike BSD we maintain a usage count on a given multicast address so - * that a casual user application can add/delete multicasts used by - * protocols without doing damage to the protocols when it deletes the - * entries. It also helps IP as it tracks overlapping maps. - * - * Device mc lists are changed by bh at least if IPv6 is enabled, - * so that it must be bh protected. - * - * We block accesses to device mc filters with netif_tx_lock. - */ - -/* - * Delete a device level multicast - */ - -int dev_mc_delete(struct net_device *dev, void *addr, int alen, int glbl) -{ - int err; - - netif_addr_lock_bh(dev); - err = __dev_addr_delete(&dev->mc_list, &dev->mc_count, - addr, alen, glbl); - if (!err) { - /* - * We have altered the list, so the card - * loaded filter is now wrong. Fix it - */ - - __dev_set_rx_mode(dev); - } - netif_addr_unlock_bh(dev); - return err; -} - -/* - * Add a device level multicast - */ - -int dev_mc_add(struct net_device *dev, void *addr, int alen, int glbl) -{ - int err; - - netif_addr_lock_bh(dev); - if (alen != dev->addr_len) - err = -EINVAL; - else - err = __dev_addr_add(&dev->mc_list, &dev->mc_count, addr, alen, glbl); - if (!err) - __dev_set_rx_mode(dev); - netif_addr_unlock_bh(dev); - return err; -} - -/** - * dev_mc_sync - Synchronize device's multicast 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_multicast_list - * or dev->set_rx_mode function of layered software devices. - */ -int dev_mc_sync(struct net_device *to, struct net_device *from) -{ - int err = 0; - - netif_addr_lock_bh(to); - err = __dev_addr_sync(&to->mc_list, &to->mc_count, - &from->mc_list, &from->mc_count); - if (!err) - __dev_set_rx_mode(to); - netif_addr_unlock_bh(to); - - return err; -} -EXPORT_SYMBOL(dev_mc_sync); - - -/** - * dev_mc_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_mc_sync(). This function is intended to be called from the - * dev->stop function of layered software devices. - */ -void dev_mc_unsync(struct net_device *to, struct net_device *from) -{ - netif_addr_lock_bh(from); - netif_addr_lock(to); - - __dev_addr_unsync(&to->mc_list, &to->mc_count, - &from->mc_list, &from->mc_count); - __dev_set_rx_mode(to); - - netif_addr_unlock(to); - netif_addr_unlock_bh(from); -} -EXPORT_SYMBOL(dev_mc_unsync); - -#ifdef CONFIG_PROC_FS -static int dev_mc_seq_show(struct seq_file *seq, void *v) -{ - struct dev_addr_list *m; - struct net_device *dev = v; - - if (v == SEQ_START_TOKEN) - return 0; - - netif_addr_lock_bh(dev); - for (m = dev->mc_list; m; m = m->next) { - int i; - - seq_printf(seq, "%-4d %-15s %-5d %-5d ", dev->ifindex, - dev->name, m->dmi_users, m->dmi_gusers); - - for (i = 0; i < m->dmi_addrlen; i++) - seq_printf(seq, "%02x", m->dmi_addr[i]); - - seq_putc(seq, '\n'); - } - netif_addr_unlock_bh(dev); - return 0; -} - -static const struct seq_operations dev_mc_seq_ops = { - .start = dev_seq_start, - .next = dev_seq_next, - .stop = dev_seq_stop, - .show = dev_mc_seq_show, -}; - -static int dev_mc_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &dev_mc_seq_ops, - sizeof(struct seq_net_private)); -} - -static const struct file_operations dev_mc_seq_fops = { - .owner = THIS_MODULE, - .open = dev_mc_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; - -#endif - -static int __net_init dev_mc_net_init(struct net *net) -{ - if (!proc_net_fops_create(net, "dev_mcast", 0, &dev_mc_seq_fops)) - return -ENOMEM; - return 0; -} - -static void __net_exit dev_mc_net_exit(struct net *net) -{ - proc_net_remove(net, "dev_mcast"); -} - -static struct pernet_operations __net_initdata dev_mc_net_ops = { - .init = dev_mc_net_init, - .exit = dev_mc_net_exit, -}; - -void __init dev_mcast_init(void) -{ - register_pernet_subsys(&dev_mc_net_ops); -} - -EXPORT_SYMBOL(dev_mc_add); -EXPORT_SYMBOL(dev_mc_delete); diff --git a/net/core/dst.c b/net/core/dst.c index f307bc18f6a..9920722cc82 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -44,7 +44,7 @@ static atomic_t dst_total = ATOMIC_INIT(0); */ static struct { spinlock_t lock; - struct dst_entry *list; + struct dst_entry *list; unsigned long timer_inc; unsigned long timer_expires; } dst_garbage = { @@ -52,7 +52,7 @@ static struct { .timer_inc = DST_GC_MAX, }; static void dst_gc_task(struct work_struct *work); -static void ___dst_free(struct dst_entry * dst); +static void ___dst_free(struct dst_entry *dst); static DECLARE_DELAYED_WORK(dst_gc_work, dst_gc_task); @@ -136,8 +136,8 @@ loop: } expires = dst_garbage.timer_expires; /* - * if the next desired timer is more than 4 seconds in the future - * then round the timer to whole seconds + * if the next desired timer is more than 4 seconds in the + * future then round the timer to whole seconds */ if (expires > 4*HZ) expires = round_jiffies_relative(expires); @@ -152,7 +152,8 @@ loop: " expires: %lu elapsed: %lu us\n", atomic_read(&dst_total), delayed, work_performed, expires, - elapsed.tv_sec * USEC_PER_SEC + elapsed.tv_nsec / NSEC_PER_USEC); + elapsed.tv_sec * USEC_PER_SEC + + elapsed.tv_nsec / NSEC_PER_USEC); #endif } @@ -163,9 +164,9 @@ int dst_discard(struct sk_buff *skb) } EXPORT_SYMBOL(dst_discard); -void * dst_alloc(struct dst_ops * ops) +void *dst_alloc(struct dst_ops *ops) { - struct dst_entry * dst; + struct dst_entry *dst; if (ops->gc && atomic_read(&ops->entries) > ops->gc_thresh) { if (ops->gc(ops)) @@ -185,19 +186,20 @@ void * dst_alloc(struct dst_ops * ops) atomic_inc(&ops->entries); return dst; } +EXPORT_SYMBOL(dst_alloc); -static void ___dst_free(struct dst_entry * dst) +static void ___dst_free(struct dst_entry *dst) { /* The first case (dev==NULL) is required, when protocol module is unloaded. */ - if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) { + if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) dst->input = dst->output = dst_discard; - } dst->obsolete = 2; } +EXPORT_SYMBOL(__dst_free); -void __dst_free(struct dst_entry * dst) +void __dst_free(struct dst_entry *dst) { spin_lock_bh(&dst_garbage.lock); ___dst_free(dst); @@ -262,15 +264,16 @@ again: } return NULL; } +EXPORT_SYMBOL(dst_destroy); void dst_release(struct dst_entry *dst) { if (dst) { - int newrefcnt; + int newrefcnt; smp_mb__before_atomic_dec(); - newrefcnt = atomic_dec_return(&dst->__refcnt); - WARN_ON(newrefcnt < 0); + newrefcnt = atomic_dec_return(&dst->__refcnt); + WARN_ON(newrefcnt < 0); } } EXPORT_SYMBOL(dst_release); @@ -283,8 +286,8 @@ EXPORT_SYMBOL(dst_release); * * Commented and originally written by Alexey. */ -static inline void dst_ifdown(struct dst_entry *dst, struct net_device *dev, - int unregister) +static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, + int unregister) { if (dst->ops->ifdown) dst->ops->ifdown(dst, dev, unregister); @@ -306,7 +309,8 @@ static inline void dst_ifdown(struct dst_entry *dst, struct net_device *dev, } } -static int dst_dev_event(struct notifier_block *this, unsigned long event, void *ptr) +static int dst_dev_event(struct notifier_block *this, unsigned long event, + void *ptr) { struct net_device *dev = ptr; struct dst_entry *dst, *last = NULL; @@ -329,9 +333,8 @@ static int dst_dev_event(struct notifier_block *this, unsigned long event, void last->next = dst; else dst_busy_list = dst; - for (; dst; dst = dst->next) { + for (; dst; dst = dst->next) dst_ifdown(dst, dev, event != NETDEV_DOWN); - } mutex_unlock(&dst_gc_mutex); break; } @@ -346,7 +349,3 @@ void __init dst_init(void) { register_netdevice_notifier(&dst_dev_notifier); } - -EXPORT_SYMBOL(__dst_free); -EXPORT_SYMBOL(dst_alloc); -EXPORT_SYMBOL(dst_destroy); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 9d55c57f318..a0f4964033d 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -18,8 +18,8 @@ #include <linux/ethtool.h> #include <linux/netdevice.h> #include <linux/bitops.h> +#include <linux/uaccess.h> #include <linux/slab.h> -#include <asm/uaccess.h> /* * Some useful ethtool_ops methods that're device independent. @@ -31,6 +31,7 @@ u32 ethtool_op_get_link(struct net_device *dev) { return netif_carrier_ok(dev) ? 1 : 0; } +EXPORT_SYMBOL(ethtool_op_get_link); u32 ethtool_op_get_rx_csum(struct net_device *dev) { @@ -63,6 +64,7 @@ int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data) return 0; } +EXPORT_SYMBOL(ethtool_op_set_tx_hw_csum); int ethtool_op_set_tx_ipv6_csum(struct net_device *dev, u32 data) { @@ -73,11 +75,13 @@ int ethtool_op_set_tx_ipv6_csum(struct net_device *dev, u32 data) return 0; } +EXPORT_SYMBOL(ethtool_op_set_tx_ipv6_csum); u32 ethtool_op_get_sg(struct net_device *dev) { return (dev->features & NETIF_F_SG) != 0; } +EXPORT_SYMBOL(ethtool_op_get_sg); int ethtool_op_set_sg(struct net_device *dev, u32 data) { @@ -88,11 +92,13 @@ int ethtool_op_set_sg(struct net_device *dev, u32 data) return 0; } +EXPORT_SYMBOL(ethtool_op_set_sg); u32 ethtool_op_get_tso(struct net_device *dev) { return (dev->features & NETIF_F_TSO) != 0; } +EXPORT_SYMBOL(ethtool_op_get_tso); int ethtool_op_set_tso(struct net_device *dev, u32 data) { @@ -103,11 +109,13 @@ int ethtool_op_set_tso(struct net_device *dev, u32 data) return 0; } +EXPORT_SYMBOL(ethtool_op_set_tso); u32 ethtool_op_get_ufo(struct net_device *dev) { return (dev->features & NETIF_F_UFO) != 0; } +EXPORT_SYMBOL(ethtool_op_get_ufo); int ethtool_op_set_ufo(struct net_device *dev, u32 data) { @@ -117,12 +125,13 @@ int ethtool_op_set_ufo(struct net_device *dev, u32 data) dev->features &= ~NETIF_F_UFO; return 0; } +EXPORT_SYMBOL(ethtool_op_set_ufo); /* the following list of flags are the same as their associated * NETIF_F_xxx values in include/linux/netdevice.h */ static const u32 flags_dup_features = - (ETH_FLAG_LRO | ETH_FLAG_NTUPLE); + (ETH_FLAG_LRO | ETH_FLAG_NTUPLE | ETH_FLAG_RXHASH); u32 ethtool_op_get_flags(struct net_device *dev) { @@ -133,6 +142,7 @@ u32 ethtool_op_get_flags(struct net_device *dev) return dev->features & flags_dup_features; } +EXPORT_SYMBOL(ethtool_op_get_flags); int ethtool_op_set_flags(struct net_device *dev, u32 data) { @@ -153,9 +163,15 @@ int ethtool_op_set_flags(struct net_device *dev, u32 data) features &= ~NETIF_F_NTUPLE; } + if (data & ETH_FLAG_RXHASH) + features |= NETIF_F_RXHASH; + else + features &= ~NETIF_F_RXHASH; + dev->features = features; return 0; } +EXPORT_SYMBOL(ethtool_op_set_flags); void ethtool_ntuple_flush(struct net_device *dev) { @@ -201,7 +217,8 @@ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) return dev->ethtool_ops->set_settings(dev, &cmd); } -static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, + void __user *useraddr) { struct ethtool_drvinfo info; const struct ethtool_ops *ops = dev->ethtool_ops; @@ -241,7 +258,7 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, void _ } static noinline_for_stack int ethtool_get_sset_info(struct net_device *dev, - void __user *useraddr) + void __user *useraddr) { struct ethtool_sset_info info; const struct ethtool_ops *ops = dev->ethtool_ops; @@ -300,7 +317,8 @@ out: return ret; } -static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, + void __user *useraddr) { struct ethtool_rxnfc cmd; @@ -313,7 +331,8 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, void __u return dev->ethtool_ops->set_rxnfc(dev, &cmd); } -static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, + void __user *useraddr) { struct ethtool_rxnfc info; const struct ethtool_ops *ops = dev->ethtool_ops; @@ -358,8 +377,8 @@ err_out: } static void __rx_ntuple_filter_add(struct ethtool_rx_ntuple_list *list, - struct ethtool_rx_ntuple_flow_spec *spec, - struct ethtool_rx_ntuple_flow_spec_container *fsc) + struct ethtool_rx_ntuple_flow_spec *spec, + struct ethtool_rx_ntuple_flow_spec_container *fsc) { /* don't add filters forever */ @@ -385,7 +404,8 @@ static void __rx_ntuple_filter_add(struct ethtool_rx_ntuple_list *list, list->count++; } -static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev, + void __user *useraddr) { struct ethtool_rx_ntuple cmd; const struct ethtool_ops *ops = dev->ethtool_ops; @@ -502,7 +522,7 @@ static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr) p += ETH_GSTRING_LEN; num_strings++; goto unknown_filter; - }; + } /* now the rest of the filters */ switch (fsc->fs.flow_type) { @@ -510,125 +530,125 @@ static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr) case UDP_V4_FLOW: case SCTP_V4_FLOW: sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.ip4src); + fsc->fs.h_u.tcp_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.tcp_ip4_spec.ip4src); + fsc->fs.m_u.tcp_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.ip4dst); + fsc->fs.h_u.tcp_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.tcp_ip4_spec.ip4dst); + fsc->fs.m_u.tcp_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tSrc Port: %d, mask: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.psrc, - fsc->fs.m_u.tcp_ip4_spec.psrc); + fsc->fs.h_u.tcp_ip4_spec.psrc, + fsc->fs.m_u.tcp_ip4_spec.psrc); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest Port: %d, mask: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.pdst, - fsc->fs.m_u.tcp_ip4_spec.pdst); + fsc->fs.h_u.tcp_ip4_spec.pdst, + fsc->fs.m_u.tcp_ip4_spec.pdst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tTOS: %d, mask: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.tos, - fsc->fs.m_u.tcp_ip4_spec.tos); + fsc->fs.h_u.tcp_ip4_spec.tos, + fsc->fs.m_u.tcp_ip4_spec.tos); p += ETH_GSTRING_LEN; num_strings++; break; case AH_ESP_V4_FLOW: case ESP_V4_FLOW: sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.ip4src); + fsc->fs.h_u.ah_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.ah_ip4_spec.ip4src); + fsc->fs.m_u.ah_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.ip4dst); + fsc->fs.h_u.ah_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.ah_ip4_spec.ip4dst); + fsc->fs.m_u.ah_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tSPI: %d, mask: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.spi, - fsc->fs.m_u.ah_ip4_spec.spi); + fsc->fs.h_u.ah_ip4_spec.spi, + fsc->fs.m_u.ah_ip4_spec.spi); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tTOS: %d, mask: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.tos, - fsc->fs.m_u.ah_ip4_spec.tos); + fsc->fs.h_u.ah_ip4_spec.tos, + fsc->fs.m_u.ah_ip4_spec.tos); p += ETH_GSTRING_LEN; num_strings++; break; case IP_USER_FLOW: sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.raw_ip4_spec.ip4src); + fsc->fs.h_u.raw_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.raw_ip4_spec.ip4src); + fsc->fs.m_u.raw_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.raw_ip4_spec.ip4dst); + fsc->fs.h_u.raw_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.raw_ip4_spec.ip4dst); + fsc->fs.m_u.raw_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; break; case IPV4_FLOW: sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4src); + fsc->fs.h_u.usr_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4src); + fsc->fs.m_u.usr_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4dst); + fsc->fs.h_u.usr_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4dst); + fsc->fs.m_u.usr_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tL4 bytes: 0x%x, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.l4_4_bytes, - fsc->fs.m_u.usr_ip4_spec.l4_4_bytes); + fsc->fs.h_u.usr_ip4_spec.l4_4_bytes, + fsc->fs.m_u.usr_ip4_spec.l4_4_bytes); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tTOS: %d, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.tos, - fsc->fs.m_u.usr_ip4_spec.tos); + fsc->fs.h_u.usr_ip4_spec.tos, + fsc->fs.m_u.usr_ip4_spec.tos); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tIP Version: %d, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip_ver, - fsc->fs.m_u.usr_ip4_spec.ip_ver); + fsc->fs.h_u.usr_ip4_spec.ip_ver, + fsc->fs.m_u.usr_ip4_spec.ip_ver); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tProtocol: %d, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.proto, - fsc->fs.m_u.usr_ip4_spec.proto); + fsc->fs.h_u.usr_ip4_spec.proto, + fsc->fs.m_u.usr_ip4_spec.proto); p += ETH_GSTRING_LEN; num_strings++; break; - }; + } sprintf(p, "\tVLAN: %d, mask: 0x%x\n", - fsc->fs.vlan_tag, fsc->fs.vlan_tag_mask); + fsc->fs.vlan_tag, fsc->fs.vlan_tag_mask); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tUser-defined: 0x%Lx\n", fsc->fs.data); @@ -641,7 +661,7 @@ static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr) sprintf(p, "\tAction: Drop\n"); else sprintf(p, "\tAction: Direct to queue %d\n", - fsc->fs.action); + fsc->fs.action); p += ETH_GSTRING_LEN; num_strings++; unknown_filter: @@ -853,7 +873,8 @@ static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) return ret; } -static noinline_for_stack int ethtool_get_coalesce(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_get_coalesce(struct net_device *dev, + void __user *useraddr) { struct ethtool_coalesce coalesce = { .cmd = ETHTOOL_GCOALESCE }; @@ -867,7 +888,8 @@ static noinline_for_stack int ethtool_get_coalesce(struct net_device *dev, void return 0; } -static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, + void __user *useraddr) { struct ethtool_coalesce coalesce; @@ -971,6 +993,7 @@ static int ethtool_set_tx_csum(struct net_device *dev, char __user *useraddr) return dev->ethtool_ops->set_tx_csum(dev, edata.data); } +EXPORT_SYMBOL(ethtool_op_set_tx_csum); static int ethtool_set_rx_csum(struct net_device *dev, char __user *useraddr) { @@ -1042,7 +1065,7 @@ static int ethtool_get_gso(struct net_device *dev, char __user *useraddr) edata.data = dev->features & NETIF_F_GSO; if (copy_to_user(useraddr, &edata, sizeof(edata))) - return -EFAULT; + return -EFAULT; return 0; } @@ -1065,7 +1088,7 @@ static int ethtool_get_gro(struct net_device *dev, char __user *useraddr) edata.data = dev->features & NETIF_F_GRO; if (copy_to_user(useraddr, &edata, sizeof(edata))) - return -EFAULT; + return -EFAULT; return 0; } @@ -1277,7 +1300,8 @@ static int ethtool_set_value(struct net_device *dev, char __user *useraddr, return actor(dev, edata.data); } -static noinline_for_stack int ethtool_flash_device(struct net_device *dev, char __user *useraddr) +static noinline_for_stack int ethtool_flash_device(struct net_device *dev, + char __user *useraddr) { struct ethtool_flash efl; @@ -1306,11 +1330,11 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) if (!dev->ethtool_ops) return -EOPNOTSUPP; - if (copy_from_user(ðcmd, useraddr, sizeof (ethcmd))) + if (copy_from_user(ðcmd, useraddr, sizeof(ethcmd))) return -EFAULT; /* Allow some commands to be done by anyone */ - switch(ethcmd) { + switch (ethcmd) { case ETHTOOL_GDRVINFO: case ETHTOOL_GMSGLVL: case ETHTOOL_GCOALESCE: @@ -1338,10 +1362,11 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) return -EPERM; } - if (dev->ethtool_ops->begin) - if ((rc = dev->ethtool_ops->begin(dev)) < 0) + if (dev->ethtool_ops->begin) { + rc = dev->ethtool_ops->begin(dev); + if (rc < 0) return rc; - + } old_features = dev->features; switch (ethcmd) { @@ -1531,16 +1556,3 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) return rc; } - -EXPORT_SYMBOL(ethtool_op_get_link); -EXPORT_SYMBOL(ethtool_op_get_sg); -EXPORT_SYMBOL(ethtool_op_get_tso); -EXPORT_SYMBOL(ethtool_op_set_sg); -EXPORT_SYMBOL(ethtool_op_set_tso); -EXPORT_SYMBOL(ethtool_op_set_tx_csum); -EXPORT_SYMBOL(ethtool_op_set_tx_hw_csum); -EXPORT_SYMBOL(ethtool_op_set_tx_ipv6_csum); -EXPORT_SYMBOL(ethtool_op_set_ufo); -EXPORT_SYMBOL(ethtool_op_get_ufo); -EXPORT_SYMBOL(ethtool_op_set_flags); -EXPORT_SYMBOL(ethtool_op_get_flags); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index d2c3e7dc2e5..42e84e08a1b 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -39,6 +39,24 @@ int fib_default_rule_add(struct fib_rules_ops *ops, } EXPORT_SYMBOL(fib_default_rule_add); +u32 fib_default_rule_pref(struct fib_rules_ops *ops) +{ + struct list_head *pos; + struct fib_rule *rule; + + if (!list_empty(&ops->rules_list)) { + pos = ops->rules_list.next; + if (pos->next != &ops->rules_list) { + rule = list_entry(pos->next, struct fib_rule, list); + if (rule->pref) + return rule->pref - 1; + } + } + + return 0; +} +EXPORT_SYMBOL(fib_default_rule_pref); + static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, u32 pid); @@ -104,12 +122,12 @@ errout: } struct fib_rules_ops * -fib_rules_register(struct fib_rules_ops *tmpl, struct net *net) +fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net) { struct fib_rules_ops *ops; int err; - ops = kmemdup(tmpl, sizeof (*ops), GFP_KERNEL); + ops = kmemdup(tmpl, sizeof(*ops), GFP_KERNEL); if (ops == NULL) return ERR_PTR(-ENOMEM); @@ -124,7 +142,6 @@ fib_rules_register(struct fib_rules_ops *tmpl, struct net *net) return ops; } - EXPORT_SYMBOL_GPL(fib_rules_register); void fib_rules_cleanup_ops(struct fib_rules_ops *ops) @@ -158,7 +175,6 @@ void fib_rules_unregister(struct fib_rules_ops *ops) call_rcu(&ops->rcu, fib_rules_put_rcu); } - EXPORT_SYMBOL_GPL(fib_rules_unregister); static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, @@ -221,7 +237,6 @@ out: return err; } - EXPORT_SYMBOL_GPL(fib_rules_lookup); static int validate_rulemsg(struct fib_rule_hdr *frh, struct nlattr **tb, @@ -520,6 +535,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, return -EMSGSIZE; frh = nlmsg_data(nlh); + frh->family = ops->family; frh->table = rule->table; NLA_PUT_U32(skb, FRA_TABLE, rule->table); frh->res1 = 0; @@ -614,7 +630,7 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) break; cb->args[1] = 0; - skip: +skip: idx++; } rcu_read_unlock(); @@ -686,7 +702,6 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event, struct fib_rules_ops *ops; ASSERT_RTNL(); - rcu_read_lock(); switch (event) { case NETDEV_REGISTER: @@ -700,8 +715,6 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event, break; } - rcu_read_unlock(); - return NOTIFY_DONE; } diff --git a/net/core/filter.c b/net/core/filter.c index ff943bed21a..da69fb728d3 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -302,6 +302,8 @@ load_b: A = skb->pkt_type; continue; case SKF_AD_IFINDEX: + if (!skb->dev) + return 0; A = skb->dev->ifindex; continue; case SKF_AD_MARK: @@ -310,6 +312,11 @@ load_b: case SKF_AD_QUEUE: A = skb->queue_mapping; continue; + case SKF_AD_HATYPE: + if (!skb->dev) + return 0; + A = skb->dev->type; + continue; case SKF_AD_NLATTR: { struct nlattr *nla; diff --git a/net/core/flow.c b/net/core/flow.c index 96015871ece..16190067400 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -26,113 +26,158 @@ #include <linux/security.h> struct flow_cache_entry { - struct flow_cache_entry *next; - u16 family; - u8 dir; - u32 genid; - struct flowi key; - void *object; - atomic_t *object_ref; + union { + struct hlist_node hlist; + struct list_head gc_list; + } u; + u16 family; + u8 dir; + u32 genid; + struct flowi key; + struct flow_cache_object *object; }; -atomic_t flow_cache_genid = ATOMIC_INIT(0); - -static u32 flow_hash_shift; -#define flow_hash_size (1 << flow_hash_shift) -static DEFINE_PER_CPU(struct flow_cache_entry **, flow_tables) = { NULL }; - -#define flow_table(cpu) (per_cpu(flow_tables, cpu)) - -static struct kmem_cache *flow_cachep __read_mostly; +struct flow_cache_percpu { + struct hlist_head *hash_table; + int hash_count; + u32 hash_rnd; + int hash_rnd_recalc; + struct tasklet_struct flush_tasklet; +}; -static int flow_lwm, flow_hwm; +struct flow_flush_info { + struct flow_cache *cache; + atomic_t cpuleft; + struct completion completion; +}; -struct flow_percpu_info { - int hash_rnd_recalc; - u32 hash_rnd; - int count; +struct flow_cache { + u32 hash_shift; + unsigned long order; + struct flow_cache_percpu *percpu; + struct notifier_block hotcpu_notifier; + int low_watermark; + int high_watermark; + struct timer_list rnd_timer; }; -static DEFINE_PER_CPU(struct flow_percpu_info, flow_hash_info) = { 0 }; -#define flow_hash_rnd_recalc(cpu) \ - (per_cpu(flow_hash_info, cpu).hash_rnd_recalc) -#define flow_hash_rnd(cpu) \ - (per_cpu(flow_hash_info, cpu).hash_rnd) -#define flow_count(cpu) \ - (per_cpu(flow_hash_info, cpu).count) +atomic_t flow_cache_genid = ATOMIC_INIT(0); +static struct flow_cache flow_cache_global; +static struct kmem_cache *flow_cachep; -static struct timer_list flow_hash_rnd_timer; +static DEFINE_SPINLOCK(flow_cache_gc_lock); +static LIST_HEAD(flow_cache_gc_list); -#define FLOW_HASH_RND_PERIOD (10 * 60 * HZ) - -struct flow_flush_info { - atomic_t cpuleft; - struct completion completion; -}; -static DEFINE_PER_CPU(struct tasklet_struct, flow_flush_tasklets) = { NULL }; - -#define flow_flush_tasklet(cpu) (&per_cpu(flow_flush_tasklets, cpu)) +#define flow_cache_hash_size(cache) (1 << (cache)->hash_shift) +#define FLOW_HASH_RND_PERIOD (10 * 60 * HZ) static void flow_cache_new_hashrnd(unsigned long arg) { + struct flow_cache *fc = (void *) arg; int i; for_each_possible_cpu(i) - flow_hash_rnd_recalc(i) = 1; + per_cpu_ptr(fc->percpu, i)->hash_rnd_recalc = 1; - flow_hash_rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD; - add_timer(&flow_hash_rnd_timer); + fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD; + add_timer(&fc->rnd_timer); +} + +static int flow_entry_valid(struct flow_cache_entry *fle) +{ + if (atomic_read(&flow_cache_genid) != fle->genid) + return 0; + if (fle->object && !fle->object->ops->check(fle->object)) + return 0; + return 1; } -static void flow_entry_kill(int cpu, struct flow_cache_entry *fle) +static void flow_entry_kill(struct flow_cache_entry *fle) { if (fle->object) - atomic_dec(fle->object_ref); + fle->object->ops->delete(fle->object); kmem_cache_free(flow_cachep, fle); - flow_count(cpu)--; } -static void __flow_cache_shrink(int cpu, int shrink_to) +static void flow_cache_gc_task(struct work_struct *work) { - struct flow_cache_entry *fle, **flp; - int i; + struct list_head gc_list; + struct flow_cache_entry *fce, *n; - for (i = 0; i < flow_hash_size; i++) { - int k = 0; + INIT_LIST_HEAD(&gc_list); + spin_lock_bh(&flow_cache_gc_lock); + list_splice_tail_init(&flow_cache_gc_list, &gc_list); + spin_unlock_bh(&flow_cache_gc_lock); - flp = &flow_table(cpu)[i]; - while ((fle = *flp) != NULL && k < shrink_to) { - k++; - flp = &fle->next; - } - while ((fle = *flp) != NULL) { - *flp = fle->next; - flow_entry_kill(cpu, fle); - } + list_for_each_entry_safe(fce, n, &gc_list, u.gc_list) + flow_entry_kill(fce); +} +static DECLARE_WORK(flow_cache_gc_work, flow_cache_gc_task); + +static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp, + int deleted, struct list_head *gc_list) +{ + if (deleted) { + fcp->hash_count -= deleted; + spin_lock_bh(&flow_cache_gc_lock); + list_splice_tail(gc_list, &flow_cache_gc_list); + spin_unlock_bh(&flow_cache_gc_lock); + schedule_work(&flow_cache_gc_work); } } -static void flow_cache_shrink(int cpu) +static void __flow_cache_shrink(struct flow_cache *fc, + struct flow_cache_percpu *fcp, + int shrink_to) { - int shrink_to = flow_lwm / flow_hash_size; + struct flow_cache_entry *fle; + struct hlist_node *entry, *tmp; + LIST_HEAD(gc_list); + int i, deleted = 0; + + for (i = 0; i < flow_cache_hash_size(fc); i++) { + int saved = 0; + + hlist_for_each_entry_safe(fle, entry, tmp, + &fcp->hash_table[i], u.hlist) { + if (saved < shrink_to && + flow_entry_valid(fle)) { + saved++; + } else { + deleted++; + hlist_del(&fle->u.hlist); + list_add_tail(&fle->u.gc_list, &gc_list); + } + } + } - __flow_cache_shrink(cpu, shrink_to); + flow_cache_queue_garbage(fcp, deleted, &gc_list); } -static void flow_new_hash_rnd(int cpu) +static void flow_cache_shrink(struct flow_cache *fc, + struct flow_cache_percpu *fcp) { - get_random_bytes(&flow_hash_rnd(cpu), sizeof(u32)); - flow_hash_rnd_recalc(cpu) = 0; + int shrink_to = fc->low_watermark / flow_cache_hash_size(fc); - __flow_cache_shrink(cpu, 0); + __flow_cache_shrink(fc, fcp, shrink_to); } -static u32 flow_hash_code(struct flowi *key, int cpu) +static void flow_new_hash_rnd(struct flow_cache *fc, + struct flow_cache_percpu *fcp) +{ + get_random_bytes(&fcp->hash_rnd, sizeof(u32)); + fcp->hash_rnd_recalc = 0; + __flow_cache_shrink(fc, fcp, 0); +} + +static u32 flow_hash_code(struct flow_cache *fc, + struct flow_cache_percpu *fcp, + struct flowi *key) { u32 *k = (u32 *) key; - return (jhash2(k, (sizeof(*key) / sizeof(u32)), flow_hash_rnd(cpu)) & - (flow_hash_size - 1)); + return (jhash2(k, (sizeof(*key) / sizeof(u32)), fcp->hash_rnd) + & (flow_cache_hash_size(fc) - 1)); } #if (BITS_PER_LONG == 64) @@ -165,114 +210,117 @@ static int flow_key_compare(struct flowi *key1, struct flowi *key2) return 0; } -void *flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir, - flow_resolve_t resolver) +struct flow_cache_object * +flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir, + flow_resolve_t resolver, void *ctx) { - struct flow_cache_entry *fle, **head; + struct flow_cache *fc = &flow_cache_global; + struct flow_cache_percpu *fcp; + struct flow_cache_entry *fle, *tfle; + struct hlist_node *entry; + struct flow_cache_object *flo; unsigned int hash; - int cpu; local_bh_disable(); - cpu = smp_processor_id(); + fcp = per_cpu_ptr(fc->percpu, smp_processor_id()); fle = NULL; + flo = NULL; /* Packet really early in init? Making flow_cache_init a * pre-smp initcall would solve this. --RR */ - if (!flow_table(cpu)) + if (!fcp->hash_table) goto nocache; - if (flow_hash_rnd_recalc(cpu)) - flow_new_hash_rnd(cpu); - hash = flow_hash_code(key, cpu); + if (fcp->hash_rnd_recalc) + flow_new_hash_rnd(fc, fcp); - head = &flow_table(cpu)[hash]; - for (fle = *head; fle; fle = fle->next) { - if (fle->family == family && - fle->dir == dir && - flow_key_compare(key, &fle->key) == 0) { - if (fle->genid == atomic_read(&flow_cache_genid)) { - void *ret = fle->object; - - if (ret) - atomic_inc(fle->object_ref); - local_bh_enable(); - - return ret; - } + hash = flow_hash_code(fc, fcp, key); + hlist_for_each_entry(tfle, entry, &fcp->hash_table[hash], u.hlist) { + if (tfle->family == family && + tfle->dir == dir && + flow_key_compare(key, &tfle->key) == 0) { + fle = tfle; break; } } - if (!fle) { - if (flow_count(cpu) > flow_hwm) - flow_cache_shrink(cpu); + if (unlikely(!fle)) { + if (fcp->hash_count > fc->high_watermark) + flow_cache_shrink(fc, fcp); fle = kmem_cache_alloc(flow_cachep, GFP_ATOMIC); if (fle) { - fle->next = *head; - *head = fle; fle->family = family; fle->dir = dir; memcpy(&fle->key, key, sizeof(*key)); fle->object = NULL; - flow_count(cpu)++; + hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]); + fcp->hash_count++; } + } else if (likely(fle->genid == atomic_read(&flow_cache_genid))) { + flo = fle->object; + if (!flo) + goto ret_object; + flo = flo->ops->get(flo); + if (flo) + goto ret_object; + } else if (fle->object) { + flo = fle->object; + flo->ops->delete(flo); + fle->object = NULL; } nocache: - { - int err; - void *obj; - atomic_t *obj_ref; - - err = resolver(net, key, family, dir, &obj, &obj_ref); - - if (fle && !err) { - fle->genid = atomic_read(&flow_cache_genid); - - if (fle->object) - atomic_dec(fle->object_ref); - - fle->object = obj; - fle->object_ref = obj_ref; - if (obj) - atomic_inc(fle->object_ref); - } - local_bh_enable(); - - if (err) - obj = ERR_PTR(err); - return obj; + flo = NULL; + if (fle) { + flo = fle->object; + fle->object = NULL; } + flo = resolver(net, key, family, dir, flo, ctx); + if (fle) { + fle->genid = atomic_read(&flow_cache_genid); + if (!IS_ERR(flo)) + fle->object = flo; + else + fle->genid--; + } else { + if (flo && !IS_ERR(flo)) + flo->ops->delete(flo); + } +ret_object: + local_bh_enable(); + return flo; } static void flow_cache_flush_tasklet(unsigned long data) { struct flow_flush_info *info = (void *)data; - int i; - int cpu; - - cpu = smp_processor_id(); - for (i = 0; i < flow_hash_size; i++) { - struct flow_cache_entry *fle; - - fle = flow_table(cpu)[i]; - for (; fle; fle = fle->next) { - unsigned genid = atomic_read(&flow_cache_genid); - - if (!fle->object || fle->genid == genid) + struct flow_cache *fc = info->cache; + struct flow_cache_percpu *fcp; + struct flow_cache_entry *fle; + struct hlist_node *entry, *tmp; + LIST_HEAD(gc_list); + int i, deleted = 0; + + fcp = per_cpu_ptr(fc->percpu, smp_processor_id()); + for (i = 0; i < flow_cache_hash_size(fc); i++) { + hlist_for_each_entry_safe(fle, entry, tmp, + &fcp->hash_table[i], u.hlist) { + if (flow_entry_valid(fle)) continue; - fle->object = NULL; - atomic_dec(fle->object_ref); + deleted++; + hlist_del(&fle->u.hlist); + list_add_tail(&fle->u.gc_list, &gc_list); } } + flow_cache_queue_garbage(fcp, deleted, &gc_list); + if (atomic_dec_and_test(&info->cpuleft)) complete(&info->completion); } -static void flow_cache_flush_per_cpu(void *) __attribute__((__unused__)); static void flow_cache_flush_per_cpu(void *data) { struct flow_flush_info *info = data; @@ -280,8 +328,7 @@ static void flow_cache_flush_per_cpu(void *data) struct tasklet_struct *tasklet; cpu = smp_processor_id(); - - tasklet = flow_flush_tasklet(cpu); + tasklet = &per_cpu_ptr(info->cache->percpu, cpu)->flush_tasklet; tasklet->data = (unsigned long)info; tasklet_schedule(tasklet); } @@ -294,6 +341,7 @@ void flow_cache_flush(void) /* Don't want cpus going down or up during this. */ get_online_cpus(); mutex_lock(&flow_flush_sem); + info.cache = &flow_cache_global; atomic_set(&info.cpuleft, num_online_cpus()); init_completion(&info.completion); @@ -307,62 +355,75 @@ void flow_cache_flush(void) put_online_cpus(); } -static void __init flow_cache_cpu_prepare(int cpu) +static void __init flow_cache_cpu_prepare(struct flow_cache *fc, + struct flow_cache_percpu *fcp) { - struct tasklet_struct *tasklet; - unsigned long order; - - for (order = 0; - (PAGE_SIZE << order) < - (sizeof(struct flow_cache_entry *)*flow_hash_size); - order++) - /* NOTHING */; - - flow_table(cpu) = (struct flow_cache_entry **) - __get_free_pages(GFP_KERNEL|__GFP_ZERO, order); - if (!flow_table(cpu)) - panic("NET: failed to allocate flow cache order %lu\n", order); - - flow_hash_rnd_recalc(cpu) = 1; - flow_count(cpu) = 0; - - tasklet = flow_flush_tasklet(cpu); - tasklet_init(tasklet, flow_cache_flush_tasklet, 0); + fcp->hash_table = (struct hlist_head *) + __get_free_pages(GFP_KERNEL|__GFP_ZERO, fc->order); + if (!fcp->hash_table) + panic("NET: failed to allocate flow cache order %lu\n", fc->order); + + fcp->hash_rnd_recalc = 1; + fcp->hash_count = 0; + tasklet_init(&fcp->flush_tasklet, flow_cache_flush_tasklet, 0); } static int flow_cache_cpu(struct notifier_block *nfb, unsigned long action, void *hcpu) { + struct flow_cache *fc = container_of(nfb, struct flow_cache, hotcpu_notifier); + int cpu = (unsigned long) hcpu; + struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); + if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) - __flow_cache_shrink((unsigned long)hcpu, 0); + __flow_cache_shrink(fc, fcp, 0); return NOTIFY_OK; } -static int __init flow_cache_init(void) +static int flow_cache_init(struct flow_cache *fc) { + unsigned long order; int i; - flow_cachep = kmem_cache_create("flow_cache", - sizeof(struct flow_cache_entry), - 0, SLAB_PANIC, - NULL); - flow_hash_shift = 10; - flow_lwm = 2 * flow_hash_size; - flow_hwm = 4 * flow_hash_size; + fc->hash_shift = 10; + fc->low_watermark = 2 * flow_cache_hash_size(fc); + fc->high_watermark = 4 * flow_cache_hash_size(fc); + + for (order = 0; + (PAGE_SIZE << order) < + (sizeof(struct hlist_head)*flow_cache_hash_size(fc)); + order++) + /* NOTHING */; + fc->order = order; + fc->percpu = alloc_percpu(struct flow_cache_percpu); - setup_timer(&flow_hash_rnd_timer, flow_cache_new_hashrnd, 0); - flow_hash_rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD; - add_timer(&flow_hash_rnd_timer); + setup_timer(&fc->rnd_timer, flow_cache_new_hashrnd, + (unsigned long) fc); + fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD; + add_timer(&fc->rnd_timer); for_each_possible_cpu(i) - flow_cache_cpu_prepare(i); + flow_cache_cpu_prepare(fc, per_cpu_ptr(fc->percpu, i)); + + fc->hotcpu_notifier = (struct notifier_block){ + .notifier_call = flow_cache_cpu, + }; + register_hotcpu_notifier(&fc->hotcpu_notifier); - hotcpu_notifier(flow_cache_cpu, 0); return 0; } -module_init(flow_cache_init); +static int __init flow_cache_init_global(void) +{ + flow_cachep = kmem_cache_create("flow_cache", + sizeof(struct flow_cache_entry), + 0, SLAB_PANIC, NULL); + + return flow_cache_init(&flow_cache_global); +} + +module_init(flow_cache_init_global); EXPORT_SYMBOL(flow_cache_genid); EXPORT_SYMBOL(flow_cache_lookup); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 59cfc7d8fc4..c57c4b228bb 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -17,6 +17,7 @@ #include <net/sock.h> #include <linux/rtnetlink.h> #include <linux/wireless.h> +#include <linux/vmalloc.h> #include <net/wext.h> #include "net-sysfs.h" @@ -467,6 +468,304 @@ static struct attribute_group wireless_group = { }; #endif +#ifdef CONFIG_RPS +/* + * RX queue sysfs structures and functions. + */ +struct rx_queue_attribute { + struct attribute attr; + ssize_t (*show)(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, char *buf); + ssize_t (*store)(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, const char *buf, size_t len); +}; +#define to_rx_queue_attr(_attr) container_of(_attr, \ + struct rx_queue_attribute, attr) + +#define to_rx_queue(obj) container_of(obj, struct netdev_rx_queue, kobj) + +static ssize_t rx_queue_attr_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); + struct netdev_rx_queue *queue = to_rx_queue(kobj); + + if (!attribute->show) + return -EIO; + + return attribute->show(queue, attribute, buf); +} + +static ssize_t rx_queue_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); + struct netdev_rx_queue *queue = to_rx_queue(kobj); + + if (!attribute->store) + return -EIO; + + return attribute->store(queue, attribute, buf, count); +} + +static struct sysfs_ops rx_queue_sysfs_ops = { + .show = rx_queue_attr_show, + .store = rx_queue_attr_store, +}; + +static ssize_t show_rps_map(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attribute, char *buf) +{ + struct rps_map *map; + cpumask_var_t mask; + size_t len = 0; + int i; + + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + rcu_read_lock(); + map = rcu_dereference(queue->rps_map); + if (map) + for (i = 0; i < map->len; i++) + cpumask_set_cpu(map->cpus[i], mask); + + len += cpumask_scnprintf(buf + len, PAGE_SIZE, mask); + if (PAGE_SIZE - len < 3) { + rcu_read_unlock(); + free_cpumask_var(mask); + return -EINVAL; + } + rcu_read_unlock(); + + free_cpumask_var(mask); + len += sprintf(buf + len, "\n"); + return len; +} + +static void rps_map_release(struct rcu_head *rcu) +{ + struct rps_map *map = container_of(rcu, struct rps_map, rcu); + + kfree(map); +} + +static ssize_t store_rps_map(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attribute, + const char *buf, size_t len) +{ + struct rps_map *old_map, *map; + cpumask_var_t mask; + int err, cpu, i; + static DEFINE_SPINLOCK(rps_map_lock); + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); + if (err) { + free_cpumask_var(mask); + return err; + } + + map = kzalloc(max_t(unsigned, + RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES), + GFP_KERNEL); + if (!map) { + free_cpumask_var(mask); + return -ENOMEM; + } + + i = 0; + for_each_cpu_and(cpu, mask, cpu_online_mask) + map->cpus[i++] = cpu; + + if (i) + map->len = i; + else { + kfree(map); + map = NULL; + } + + spin_lock(&rps_map_lock); + old_map = queue->rps_map; + rcu_assign_pointer(queue->rps_map, map); + spin_unlock(&rps_map_lock); + + if (old_map) + call_rcu(&old_map->rcu, rps_map_release); + + free_cpumask_var(mask); + return len; +} + +static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, + char *buf) +{ + struct rps_dev_flow_table *flow_table; + unsigned int val = 0; + + rcu_read_lock(); + flow_table = rcu_dereference(queue->rps_flow_table); + if (flow_table) + val = flow_table->mask + 1; + rcu_read_unlock(); + + return sprintf(buf, "%u\n", val); +} + +static void rps_dev_flow_table_release_work(struct work_struct *work) +{ + struct rps_dev_flow_table *table = container_of(work, + struct rps_dev_flow_table, free_work); + + vfree(table); +} + +static void rps_dev_flow_table_release(struct rcu_head *rcu) +{ + struct rps_dev_flow_table *table = container_of(rcu, + struct rps_dev_flow_table, rcu); + + INIT_WORK(&table->free_work, rps_dev_flow_table_release_work); + schedule_work(&table->free_work); +} + +static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, + const char *buf, size_t len) +{ + unsigned int count; + char *endp; + struct rps_dev_flow_table *table, *old_table; + static DEFINE_SPINLOCK(rps_dev_flow_lock); + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + count = simple_strtoul(buf, &endp, 0); + if (endp == buf) + return -EINVAL; + + if (count) { + int i; + + if (count > 1<<30) { + /* Enforce a limit to prevent overflow */ + return -EINVAL; + } + count = roundup_pow_of_two(count); + table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(count)); + if (!table) + return -ENOMEM; + + table->mask = count - 1; + for (i = 0; i < count; i++) + table->flows[i].cpu = RPS_NO_CPU; + } else + table = NULL; + + spin_lock(&rps_dev_flow_lock); + old_table = queue->rps_flow_table; + rcu_assign_pointer(queue->rps_flow_table, table); + spin_unlock(&rps_dev_flow_lock); + + if (old_table) + call_rcu(&old_table->rcu, rps_dev_flow_table_release); + + return len; +} + +static struct rx_queue_attribute rps_cpus_attribute = + __ATTR(rps_cpus, S_IRUGO | S_IWUSR, show_rps_map, store_rps_map); + + +static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute = + __ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR, + show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); + +static struct attribute *rx_queue_default_attrs[] = { + &rps_cpus_attribute.attr, + &rps_dev_flow_table_cnt_attribute.attr, + NULL +}; + +static void rx_queue_release(struct kobject *kobj) +{ + struct netdev_rx_queue *queue = to_rx_queue(kobj); + struct netdev_rx_queue *first = queue->first; + + if (queue->rps_map) + call_rcu(&queue->rps_map->rcu, rps_map_release); + + if (queue->rps_flow_table) + call_rcu(&queue->rps_flow_table->rcu, + rps_dev_flow_table_release); + + if (atomic_dec_and_test(&first->count)) + kfree(first); +} + +static struct kobj_type rx_queue_ktype = { + .sysfs_ops = &rx_queue_sysfs_ops, + .release = rx_queue_release, + .default_attrs = rx_queue_default_attrs, +}; + +static int rx_queue_add_kobject(struct net_device *net, int index) +{ + struct netdev_rx_queue *queue = net->_rx + index; + struct kobject *kobj = &queue->kobj; + int error = 0; + + kobj->kset = net->queues_kset; + error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, + "rx-%u", index); + if (error) { + kobject_put(kobj); + return error; + } + + kobject_uevent(kobj, KOBJ_ADD); + + return error; +} + +static int rx_queue_register_kobjects(struct net_device *net) +{ + int i; + int error = 0; + + net->queues_kset = kset_create_and_add("queues", + NULL, &net->dev.kobj); + if (!net->queues_kset) + return -ENOMEM; + for (i = 0; i < net->num_rx_queues; i++) { + error = rx_queue_add_kobject(net, i); + if (error) + break; + } + + if (error) + while (--i >= 0) + kobject_put(&net->_rx[i].kobj); + + return error; +} + +static void rx_queue_remove_kobjects(struct net_device *net) +{ + int i; + + for (i = 0; i < net->num_rx_queues; i++) + kobject_put(&net->_rx[i].kobj); + kset_unregister(net->queues_kset); +} +#endif /* CONFIG_RPS */ #endif /* CONFIG_SYSFS */ #ifdef CONFIG_HOTPLUG @@ -530,6 +829,10 @@ void netdev_unregister_kobject(struct net_device * net) if (!net_eq(dev_net(net), &init_net)) return; +#ifdef CONFIG_RPS + rx_queue_remove_kobjects(net); +#endif + device_del(dev); } @@ -538,6 +841,7 @@ int netdev_register_kobject(struct net_device *net) { struct device *dev = &(net->dev); const struct attribute_group **groups = net->sysfs_groups; + int error = 0; dev->class = &net_class; dev->platform_data = net; @@ -564,7 +868,19 @@ int netdev_register_kobject(struct net_device *net) if (!net_eq(dev_net(net), &init_net)) return 0; - return device_add(dev); + error = device_add(dev); + if (error) + return error; + +#ifdef CONFIG_RPS + error = rx_queue_register_kobjects(net); + if (error) { + device_del(dev); + return error; + } +#endif + + return error; } int netdev_class_create_file(struct class_attribute *class_attr) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index bd8c4712ea2..c988e685433 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -27,6 +27,51 @@ EXPORT_SYMBOL(init_net); #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ +static void net_generic_release(struct rcu_head *rcu) +{ + struct net_generic *ng; + + ng = container_of(rcu, struct net_generic, rcu); + kfree(ng); +} + +static int net_assign_generic(struct net *net, int id, void *data) +{ + struct net_generic *ng, *old_ng; + + BUG_ON(!mutex_is_locked(&net_mutex)); + BUG_ON(id == 0); + + ng = old_ng = net->gen; + if (old_ng->len >= id) + goto assign; + + ng = kzalloc(sizeof(struct net_generic) + + id * sizeof(void *), GFP_KERNEL); + if (ng == NULL) + return -ENOMEM; + + /* + * Some synchronisation notes: + * + * The net_generic explores the net->gen array inside rcu + * read section. Besides once set the net->gen->ptr[x] + * pointer never changes (see rules in netns/generic.h). + * + * That said, we simply duplicate this array and schedule + * the old copy for kfree after a grace period. + */ + + ng->len = id; + memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*)); + + rcu_assign_pointer(net->gen, ng); + call_rcu(&old_ng->rcu, net_generic_release); +assign: + ng->ptr[id - 1] = data; + return 0; +} + static int ops_init(const struct pernet_operations *ops, struct net *net) { int err; @@ -469,10 +514,10 @@ EXPORT_SYMBOL_GPL(register_pernet_subsys); * addition run the exit method for all existing network * namespaces. */ -void unregister_pernet_subsys(struct pernet_operations *module) +void unregister_pernet_subsys(struct pernet_operations *ops) { mutex_lock(&net_mutex); - unregister_pernet_operations(module); + unregister_pernet_operations(ops); mutex_unlock(&net_mutex); } EXPORT_SYMBOL_GPL(unregister_pernet_subsys); @@ -526,49 +571,3 @@ void unregister_pernet_device(struct pernet_operations *ops) mutex_unlock(&net_mutex); } EXPORT_SYMBOL_GPL(unregister_pernet_device); - -static void net_generic_release(struct rcu_head *rcu) -{ - struct net_generic *ng; - - ng = container_of(rcu, struct net_generic, rcu); - kfree(ng); -} - -int net_assign_generic(struct net *net, int id, void *data) -{ - struct net_generic *ng, *old_ng; - - BUG_ON(!mutex_is_locked(&net_mutex)); - BUG_ON(id == 0); - - ng = old_ng = net->gen; - if (old_ng->len >= id) - goto assign; - - ng = kzalloc(sizeof(struct net_generic) + - id * sizeof(void *), GFP_KERNEL); - if (ng == NULL) - return -ENOMEM; - - /* - * Some synchronisation notes: - * - * The net_generic explores the net->gen array inside rcu - * read section. Besides once set the net->gen->ptr[x] - * pointer never changes (see rules in netns/generic.h). - * - * That said, we simply duplicate this array and schedule - * the old copy for kfree after a grace period. - */ - - ng->len = id; - memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*)); - - rcu_assign_pointer(net->gen, ng); - call_rcu(&old_ng->rcu, net_generic_release); -assign: - ng->ptr[id - 1] = data; - return 0; -} -EXPORT_SYMBOL_GPL(net_assign_generic); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index a58f59b9759..94825b10955 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -179,9 +179,8 @@ static void service_arp_queue(struct netpoll_info *npi) } } -void netpoll_poll(struct netpoll *np) +void netpoll_poll_dev(struct net_device *dev) { - struct net_device *dev = np->dev; const struct net_device_ops *ops; if (!dev || !netif_running(dev)) @@ -201,6 +200,11 @@ void netpoll_poll(struct netpoll *np) zap_completion_queue(); } +void netpoll_poll(struct netpoll *np) +{ + netpoll_poll_dev(np->dev); +} + static void refill_skbs(void) { struct sk_buff *skb; @@ -282,7 +286,7 @@ static int netpoll_owner_active(struct net_device *dev) return 0; } -static void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) +void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) { int status = NETDEV_TX_BUSY; unsigned long tries; @@ -308,7 +312,9 @@ static void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) tries > 0; --tries) { if (__netif_tx_trylock(txq)) { if (!netif_tx_queue_stopped(txq)) { + dev->priv_flags |= IFF_IN_NETPOLL; status = ops->ndo_start_xmit(skb, dev); + dev->priv_flags &= ~IFF_IN_NETPOLL; if (status == NETDEV_TX_OK) txq_trans_update(txq); } @@ -756,7 +762,10 @@ int netpoll_setup(struct netpoll *np) atomic_inc(&npinfo->refcnt); } - if (!ndev->netdev_ops->ndo_poll_controller) { + npinfo->netpoll = np; + + if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) || + !ndev->netdev_ops->ndo_poll_controller) { printk(KERN_ERR "%s: %s doesn't support polling, aborting.\n", np->name, np->dev_name); err = -ENOTSUPP; @@ -878,6 +887,7 @@ void netpoll_cleanup(struct netpoll *np) } if (atomic_dec_and_test(&npinfo->refcnt)) { + const struct net_device_ops *ops; skb_queue_purge(&npinfo->arp_tx); skb_queue_purge(&npinfo->txq); cancel_rearming_delayed_work(&npinfo->tx_work); @@ -885,7 +895,11 @@ void netpoll_cleanup(struct netpoll *np) /* clean after last, unfinished work */ __skb_queue_purge(&npinfo->txq); kfree(npinfo); - np->dev->npinfo = NULL; + ops = np->dev->netdev_ops; + if (ops->ndo_netpoll_cleanup) + ops->ndo_netpoll_cleanup(np->dev); + else + np->dev->npinfo = NULL; } } @@ -908,6 +922,7 @@ void netpoll_set_trap(int trap) atomic_dec(&trapped); } +EXPORT_SYMBOL(netpoll_send_skb); EXPORT_SYMBOL(netpoll_set_trap); EXPORT_SYMBOL(netpoll_trap); EXPORT_SYMBOL(netpoll_print_options); @@ -915,4 +930,5 @@ EXPORT_SYMBOL(netpoll_parse_options); EXPORT_SYMBOL(netpoll_setup); EXPORT_SYMBOL(netpoll_cleanup); EXPORT_SYMBOL(netpoll_send_udp); +EXPORT_SYMBOL(netpoll_poll_dev); EXPORT_SYMBOL(netpoll_poll); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 43923811bd6..2ad68da418d 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -169,7 +169,7 @@ #include <asm/dma.h> #include <asm/div64.h> /* do_div */ -#define VERSION "2.72" +#define VERSION "2.73" #define IP_NAME_SZ 32 #define MAX_MPLS_LABELS 16 /* This is the max label stack depth */ #define MPLS_STACK_BOTTOM htonl(0x00000100) @@ -190,6 +190,7 @@ #define F_IPSEC_ON (1<<12) /* ipsec on for flows */ #define F_QUEUE_MAP_RND (1<<13) /* queue map Random */ #define F_QUEUE_MAP_CPU (1<<14) /* queue map mirrors smp_processor_id() */ +#define F_NODE (1<<15) /* Node memory alloc*/ /* Thread control flag bits */ #define T_STOP (1<<0) /* Stop run */ @@ -372,6 +373,7 @@ struct pktgen_dev { u16 queue_map_min; u16 queue_map_max; + int node; /* Memory node */ #ifdef CONFIG_XFRM __u8 ipsmode; /* IPSEC mode (config) */ @@ -607,6 +609,9 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->traffic_class) seq_printf(seq, " traffic_class: 0x%02x\n", pkt_dev->traffic_class); + if (pkt_dev->node >= 0) + seq_printf(seq, " node: %d\n", pkt_dev->node); + seq_printf(seq, " Flags: "); if (pkt_dev->flags & F_IPV6) @@ -660,6 +665,9 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->flags & F_SVID_RND) seq_printf(seq, "SVID_RND "); + if (pkt_dev->flags & F_NODE) + seq_printf(seq, "NODE_ALLOC "); + seq_puts(seq, "\n"); /* not really stopped, more like last-running-at */ @@ -1074,6 +1082,21 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->dst_mac_count); return count; } + if (!strcmp(name, "node")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + + i += len; + + if (node_possible(value)) { + pkt_dev->node = value; + sprintf(pg_result, "OK: node=%d", pkt_dev->node); + } + else + sprintf(pg_result, "ERROR: node not possible"); + return count; + } if (!strcmp(name, "flag")) { char f[32]; memset(f, 0, 32); @@ -1166,12 +1189,18 @@ static ssize_t pktgen_if_write(struct file *file, else if (strcmp(f, "!IPV6") == 0) pkt_dev->flags &= ~F_IPV6; + else if (strcmp(f, "NODE_ALLOC") == 0) + pkt_dev->flags |= F_NODE; + + else if (strcmp(f, "!NODE_ALLOC") == 0) + pkt_dev->flags &= ~F_NODE; + else { sprintf(pg_result, "Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s", f, "IPSRC_RND, IPDST_RND, UDPSRC_RND, UDPDST_RND, " - "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, IPSEC\n"); + "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, IPSEC, NODE_ALLOC\n"); return count; } sprintf(pg_result, "OK: flags=0x%x", pkt_dev->flags); @@ -2572,9 +2601,27 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, mod_cur_headers(pkt_dev); datalen = (odev->hard_header_len + 16) & ~0xf; - skb = __netdev_alloc_skb(odev, - pkt_dev->cur_pkt_size + 64 - + datalen + pkt_dev->pkt_overhead, GFP_NOWAIT); + + if (pkt_dev->flags & F_NODE) { + int node; + + if (pkt_dev->node >= 0) + node = pkt_dev->node; + else + node = numa_node_id(); + + skb = __alloc_skb(NET_SKB_PAD + pkt_dev->cur_pkt_size + 64 + + datalen + pkt_dev->pkt_overhead, GFP_NOWAIT, 0, node); + if (likely(skb)) { + skb_reserve(skb, NET_SKB_PAD); + skb->dev = odev; + } + } + else + skb = __netdev_alloc_skb(odev, + pkt_dev->cur_pkt_size + 64 + + datalen + pkt_dev->pkt_overhead, GFP_NOWAIT); + if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; @@ -3674,6 +3721,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->svlan_p = 0; pkt_dev->svlan_cfi = 0; pkt_dev->svlan_id = 0xffff; + pkt_dev->node = -1; err = pktgen_setup_dev(pkt_dev, ifname); if (err) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 31e85d327aa..e4b9870e470 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -98,7 +98,7 @@ int lockdep_rtnl_is_held(void) EXPORT_SYMBOL(lockdep_rtnl_is_held); #endif /* #ifdef CONFIG_PROVE_LOCKING */ -static struct rtnl_link *rtnl_msg_handlers[NPROTO]; +static struct rtnl_link *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1]; static inline int rtm_msgindex(int msgtype) { @@ -118,7 +118,11 @@ static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex) { struct rtnl_link *tab; - tab = rtnl_msg_handlers[protocol]; + if (protocol <= RTNL_FAMILY_MAX) + tab = rtnl_msg_handlers[protocol]; + else + tab = NULL; + if (tab == NULL || tab[msgindex].doit == NULL) tab = rtnl_msg_handlers[PF_UNSPEC]; @@ -129,7 +133,11 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) { struct rtnl_link *tab; - tab = rtnl_msg_handlers[protocol]; + if (protocol <= RTNL_FAMILY_MAX) + tab = rtnl_msg_handlers[protocol]; + else + tab = NULL; + if (tab == NULL || tab[msgindex].dumpit == NULL) tab = rtnl_msg_handlers[PF_UNSPEC]; @@ -159,7 +167,7 @@ int __rtnl_register(int protocol, int msgtype, struct rtnl_link *tab; int msgindex; - BUG_ON(protocol < 0 || protocol >= NPROTO); + BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); msgindex = rtm_msgindex(msgtype); tab = rtnl_msg_handlers[protocol]; @@ -211,7 +219,7 @@ int rtnl_unregister(int protocol, int msgtype) { int msgindex; - BUG_ON(protocol < 0 || protocol >= NPROTO); + BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); msgindex = rtm_msgindex(msgtype); if (rtnl_msg_handlers[protocol] == NULL) @@ -233,7 +241,7 @@ EXPORT_SYMBOL_GPL(rtnl_unregister); */ void rtnl_unregister_all(int protocol) { - BUG_ON(protocol < 0 || protocol >= NPROTO); + BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); kfree(rtnl_msg_handlers[protocol]); rtnl_msg_handlers[protocol] = NULL; @@ -600,7 +608,41 @@ static void copy_rtnl_link_stats(struct rtnl_link_stats *a, a->rx_compressed = b->rx_compressed; a->tx_compressed = b->tx_compressed; -}; +} + +static void copy_rtnl_link_stats64(void *v, const struct net_device_stats *b) +{ + struct rtnl_link_stats64 a; + + a.rx_packets = b->rx_packets; + a.tx_packets = b->tx_packets; + a.rx_bytes = b->rx_bytes; + a.tx_bytes = b->tx_bytes; + a.rx_errors = b->rx_errors; + a.tx_errors = b->tx_errors; + a.rx_dropped = b->rx_dropped; + a.tx_dropped = b->tx_dropped; + + a.multicast = b->multicast; + a.collisions = b->collisions; + + a.rx_length_errors = b->rx_length_errors; + a.rx_over_errors = b->rx_over_errors; + a.rx_crc_errors = b->rx_crc_errors; + a.rx_frame_errors = b->rx_frame_errors; + a.rx_fifo_errors = b->rx_fifo_errors; + a.rx_missed_errors = b->rx_missed_errors; + + a.tx_aborted_errors = b->tx_aborted_errors; + a.tx_carrier_errors = b->tx_carrier_errors; + a.tx_fifo_errors = b->tx_fifo_errors; + a.tx_heartbeat_errors = b->tx_heartbeat_errors; + a.tx_window_errors = b->tx_window_errors; + + a.rx_compressed = b->rx_compressed; + a.tx_compressed = b->tx_compressed; + memcpy(v, &a, sizeof(a)); +} /* All VF info */ static inline int rtnl_vfinfo_size(const struct net_device *dev) @@ -618,6 +660,31 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev) return 0; } +static size_t rtnl_port_size(const struct net_device *dev) +{ + size_t port_size = nla_total_size(4) /* PORT_VF */ + + nla_total_size(PORT_PROFILE_MAX) /* PORT_PROFILE */ + + nla_total_size(sizeof(struct ifla_port_vsi)) + /* PORT_VSI_TYPE */ + + nla_total_size(PORT_UUID_MAX) /* PORT_INSTANCE_UUID */ + + nla_total_size(PORT_UUID_MAX) /* PORT_HOST_UUID */ + + nla_total_size(1) /* PROT_VDP_REQUEST */ + + nla_total_size(2); /* PORT_VDP_RESPONSE */ + size_t vf_ports_size = nla_total_size(sizeof(struct nlattr)); + size_t vf_port_size = nla_total_size(sizeof(struct nlattr)) + + port_size; + size_t port_self_size = nla_total_size(sizeof(struct nlattr)) + + port_size; + + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + return 0; + if (dev_num_vf(dev->dev.parent)) + return port_self_size + vf_ports_size + + vf_port_size * dev_num_vf(dev->dev.parent); + else + return port_self_size; +} + static inline size_t if_nlmsg_size(const struct net_device *dev) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) @@ -626,6 +693,7 @@ static inline size_t if_nlmsg_size(const struct net_device *dev) + nla_total_size(IFNAMSIZ) /* IFLA_QDISC */ + nla_total_size(sizeof(struct rtnl_link_ifmap)) + nla_total_size(sizeof(struct rtnl_link_stats)) + + nla_total_size(sizeof(struct rtnl_link_stats64)) + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + nla_total_size(MAX_ADDR_LEN) /* IFLA_BROADCAST */ + nla_total_size(4) /* IFLA_TXQLEN */ @@ -637,9 +705,82 @@ static inline size_t if_nlmsg_size(const struct net_device *dev) + nla_total_size(1) /* IFLA_LINKMODE */ + nla_total_size(4) /* IFLA_NUM_VF */ + rtnl_vfinfo_size(dev) /* IFLA_VFINFO_LIST */ + + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev); /* IFLA_LINKINFO */ } +static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) +{ + struct nlattr *vf_ports; + struct nlattr *vf_port; + int vf; + int err; + + vf_ports = nla_nest_start(skb, IFLA_VF_PORTS); + if (!vf_ports) + return -EMSGSIZE; + + for (vf = 0; vf < dev_num_vf(dev->dev.parent); vf++) { + vf_port = nla_nest_start(skb, IFLA_VF_PORT); + if (!vf_port) { + nla_nest_cancel(skb, vf_ports); + return -EMSGSIZE; + } + NLA_PUT_U32(skb, IFLA_PORT_VF, vf); + err = dev->netdev_ops->ndo_get_vf_port(dev, vf, skb); + if (err) { +nla_put_failure: + nla_nest_cancel(skb, vf_port); + continue; + } + nla_nest_end(skb, vf_port); + } + + nla_nest_end(skb, vf_ports); + + return 0; +} + +static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev) +{ + struct nlattr *port_self; + int err; + + port_self = nla_nest_start(skb, IFLA_PORT_SELF); + if (!port_self) + return -EMSGSIZE; + + err = dev->netdev_ops->ndo_get_vf_port(dev, PORT_SELF_VF, skb); + if (err) { + nla_nest_cancel(skb, port_self); + return err; + } + + nla_nest_end(skb, port_self); + + return 0; +} + +static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) +{ + int err; + + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + return 0; + + err = rtnl_port_self_fill(skb, dev); + if (err) + return err; + + if (dev_num_vf(dev->dev.parent)) { + err = rtnl_vf_ports_fill(skb, dev); + if (err) + return err; + } + + return 0; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags) @@ -705,13 +846,21 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, stats = dev_get_stats(dev); copy_rtnl_link_stats(nla_data(attr), stats); + attr = nla_reserve(skb, IFLA_STATS64, + sizeof(struct rtnl_link_stats64)); + if (attr == NULL) + goto nla_put_failure; + copy_rtnl_link_stats64(nla_data(attr), stats); + + if (dev->dev.parent) + NLA_PUT_U32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent)); + if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) { int i; struct nlattr *vfinfo, *vf; int num_vfs = dev_num_vf(dev->dev.parent); - NLA_PUT_U32(skb, IFLA_NUM_VF, num_vfs); vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST); if (!vfinfo) goto nla_put_failure; @@ -739,6 +888,10 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, } nla_nest_end(skb, vfinfo); } + + if (rtnl_port_fill(skb, dev)) + goto nla_put_failure; + if (dev->rtnl_link_ops) { if (rtnl_link_fill(skb, dev) < 0) goto nla_put_failure; @@ -800,6 +953,8 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_NET_NS_PID] = { .type = NLA_U32 }, [IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 }, [IFLA_VFINFO_LIST] = {. type = NLA_NESTED }, + [IFLA_VF_PORTS] = { .type = NLA_NESTED }, + [IFLA_PORT_SELF] = { .type = NLA_NESTED }, }; EXPORT_SYMBOL(ifla_policy); @@ -821,6 +976,20 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { .len = sizeof(struct ifla_vf_tx_rate) }, }; +static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { + [IFLA_PORT_VF] = { .type = NLA_U32 }, + [IFLA_PORT_PROFILE] = { .type = NLA_STRING, + .len = PORT_PROFILE_MAX }, + [IFLA_PORT_VSI_TYPE] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_port_vsi)}, + [IFLA_PORT_INSTANCE_UUID] = { .type = NLA_BINARY, + .len = PORT_UUID_MAX }, + [IFLA_PORT_HOST_UUID] = { .type = NLA_STRING, + .len = PORT_UUID_MAX }, + [IFLA_PORT_REQUEST] = { .type = NLA_U8, }, + [IFLA_PORT_RESPONSE] = { .type = NLA_U16, }, +}; + struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) { struct net *net; @@ -1040,6 +1209,53 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, } err = 0; + if (tb[IFLA_VF_PORTS]) { + struct nlattr *port[IFLA_PORT_MAX+1]; + struct nlattr *attr; + int vf; + int rem; + + err = -EOPNOTSUPP; + if (!ops->ndo_set_vf_port) + goto errout; + + nla_for_each_nested(attr, tb[IFLA_VF_PORTS], rem) { + if (nla_type(attr) != IFLA_VF_PORT) + continue; + err = nla_parse_nested(port, IFLA_PORT_MAX, + attr, ifla_port_policy); + if (err < 0) + goto errout; + if (!port[IFLA_PORT_VF]) { + err = -EOPNOTSUPP; + goto errout; + } + vf = nla_get_u32(port[IFLA_PORT_VF]); + err = ops->ndo_set_vf_port(dev, vf, port); + if (err < 0) + goto errout; + modified = 1; + } + } + err = 0; + + if (tb[IFLA_PORT_SELF]) { + struct nlattr *port[IFLA_PORT_MAX+1]; + + err = nla_parse_nested(port, IFLA_PORT_MAX, + tb[IFLA_PORT_SELF], ifla_port_policy); + if (err < 0) + goto errout; + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_port) + err = ops->ndo_set_vf_port(dev, PORT_SELF_VF, port); + if (err < 0) + goto errout; + modified = 1; + } + err = 0; + errout: if (err < 0 && modified && net_ratelimit()) printk(KERN_WARNING "A link change request failed with " @@ -1397,7 +1613,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) if (s_idx == 0) s_idx = 1; - for (idx = 1; idx < NPROTO; idx++) { + for (idx = 1; idx <= RTNL_FAMILY_MAX; idx++) { int type = cb->nlh->nlmsg_type-RTM_BASE; if (idx < s_idx || idx == PF_PACKET) continue; @@ -1465,9 +1681,6 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return 0; family = ((struct rtgenmsg *)NLMSG_DATA(nlh))->rtgen_family; - if (family >= NPROTO) - return -EAFNOSUPPORT; - sz_idx = type>>2; kind = type&3; @@ -1535,6 +1748,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_POST_INIT: case NETDEV_REGISTER: case NETDEV_CHANGE: + case NETDEV_PRE_TYPE_CHANGE: case NETDEV_GOING_DOWN: case NETDEV_UNREGISTER: case NETDEV_UNREGISTER_BATCH: diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 93c4e060c91..c543dd25243 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -117,7 +117,7 @@ static const struct pipe_buf_operations sock_pipe_buf_ops = { * * Out of line support code for skb_put(). Not user callable. */ -void skb_over_panic(struct sk_buff *skb, int sz, void *here) +static void skb_over_panic(struct sk_buff *skb, int sz, void *here) { printk(KERN_EMERG "skb_over_panic: text:%p len:%d put:%d head:%p " "data:%p tail:%#lx end:%#lx dev:%s\n", @@ -126,7 +126,6 @@ void skb_over_panic(struct sk_buff *skb, int sz, void *here) skb->dev ? skb->dev->name : "<NULL>"); BUG(); } -EXPORT_SYMBOL(skb_over_panic); /** * skb_under_panic - private function @@ -137,7 +136,7 @@ EXPORT_SYMBOL(skb_over_panic); * Out of line support code for skb_push(). Not user callable. */ -void skb_under_panic(struct sk_buff *skb, int sz, void *here) +static void skb_under_panic(struct sk_buff *skb, int sz, void *here) { printk(KERN_EMERG "skb_under_panic: text:%p len:%d put:%d head:%p " "data:%p tail:%#lx end:%#lx dev:%s\n", @@ -146,7 +145,6 @@ void skb_under_panic(struct sk_buff *skb, int sz, void *here) skb->dev ? skb->dev->name : "<NULL>"); BUG(); } -EXPORT_SYMBOL(skb_under_panic); /* Allocate a new skbuff. We do this ourselves so we can fill in a few * 'private' fields and also do memory statistics to find all the @@ -183,12 +181,14 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node); if (!skb) goto out; + prefetchw(skb); size = SKB_DATA_ALIGN(size); data = kmalloc_node_track_caller(size + sizeof(struct skb_shared_info), gfp_mask, node); if (!data) goto nodata; + prefetchw(data + size); /* * Only clear those fields we need to clear, not those that we will @@ -210,15 +210,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, /* make sure we initialize shinfo sequentially */ shinfo = skb_shinfo(skb); + memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); - shinfo->nr_frags = 0; - shinfo->gso_size = 0; - shinfo->gso_segs = 0; - shinfo->gso_type = 0; - shinfo->ip6_frag_id = 0; - shinfo->tx_flags.flags = 0; - skb_frag_list_init(skb); - memset(&shinfo->hwtstamps, 0, sizeof(shinfo->hwtstamps)); if (fclone) { struct sk_buff *child = skb + 1; @@ -507,16 +500,10 @@ int skb_recycle_check(struct sk_buff *skb, int skb_size) return 0; skb_release_head_state(skb); + shinfo = skb_shinfo(skb); + memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); - shinfo->nr_frags = 0; - shinfo->gso_size = 0; - shinfo->gso_segs = 0; - shinfo->gso_type = 0; - shinfo->ip6_frag_id = 0; - shinfo->tx_flags.flags = 0; - skb_frag_list_init(skb); - memset(&shinfo->hwtstamps, 0, sizeof(shinfo->hwtstamps)); memset(skb, 0, offsetof(struct sk_buff, tail)); skb->data = skb->head + NET_SKB_PAD; @@ -533,7 +520,8 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->transport_header = old->transport_header; new->network_header = old->network_header; new->mac_header = old->mac_header; - skb_dst_set(new, dst_clone(skb_dst(old))); + skb_dst_copy(new, old); + new->rxhash = old->rxhash; #ifdef CONFIG_XFRM new->sp = secpath_get(old->sp); #endif @@ -581,6 +569,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) C(len); C(data_len); C(mac_len); + C(rxhash); n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len; n->cloned = 1; n->nohdr = 0; @@ -1051,7 +1040,7 @@ EXPORT_SYMBOL(skb_push); */ unsigned char *skb_pull(struct sk_buff *skb, unsigned int len) { - return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); + return skb_pull_inline(skb, len); } EXPORT_SYMBOL(skb_pull); diff --git a/net/core/sock.c b/net/core/sock.c index c5812bbc2cc..bf88a167c8f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -307,6 +307,11 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ skb_len = skb->len; + /* we escape from rcu protected region, make sure we dont leak + * a norefcounted dst + */ + skb_dst_force(skb); + spin_lock_irqsave(&list->lock, flags); skb->dropcount = atomic_read(&sk->sk_drops); __skb_queue_tail(list, skb); @@ -327,6 +332,10 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) skb->dev = NULL; + if (sk_rcvqueues_full(sk, skb)) { + atomic_inc(&sk->sk_drops); + goto discard_and_relse; + } if (nested) bh_lock_sock_nested(sk); else @@ -364,11 +373,11 @@ EXPORT_SYMBOL(sk_reset_txq); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { - struct dst_entry *dst = sk->sk_dst_cache; + struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { sk_tx_queue_clear(sk); - sk->sk_dst_cache = NULL; + rcu_assign_pointer(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; } @@ -1157,7 +1166,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) skb_queue_head_init(&newsk->sk_async_wait_queue); #endif - rwlock_init(&newsk->sk_dst_lock); + spin_lock_init(&newsk->sk_dst_lock); rwlock_init(&newsk->sk_callback_lock); lockdep_set_class_and_name(&newsk->sk_callback_lock, af_callback_keys + newsk->sk_family, @@ -1207,7 +1216,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) */ sk_refcnt_debug_inc(newsk); sk_set_socket(newsk, NULL); - newsk->sk_sleep = NULL; + newsk->sk_wq = NULL; if (newsk->sk_prot->sockets_allocated) percpu_counter_inc(newsk->sk_prot->sockets_allocated); @@ -1227,6 +1236,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) sk->sk_route_caps = dst->dev->features; if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; + sk->sk_route_caps &= ~sk->sk_route_nocaps; if (sk_can_gso(sk)) { if (dst->header_len) { sk->sk_route_caps &= ~NETIF_F_GSO_MASK; @@ -1395,7 +1405,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) if (signal_pending(current)) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) break; if (sk->sk_shutdown & SEND_SHUTDOWN) @@ -1404,7 +1414,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) break; timeo = schedule_timeout(timeo); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return timeo; } @@ -1531,6 +1541,7 @@ static void __release_sock(struct sock *sk) do { struct sk_buff *next = skb->next; + WARN_ON_ONCE(skb_dst_is_noref(skb)); skb->next = NULL; sk_backlog_rcv(sk, skb); @@ -1570,11 +1581,11 @@ int sk_wait_data(struct sock *sk, long *timeo) int rc; DEFINE_WAIT(wait); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue)); clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return rc; } EXPORT_SYMBOL(sk_wait_data); @@ -1796,41 +1807,53 @@ EXPORT_SYMBOL(sock_no_sendpage); static void sock_def_wakeup(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk_has_sleeper(sk)) - wake_up_interruptible_all(sk->sk_sleep); - read_unlock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_all(&wq->wait); + rcu_read_unlock(); } static void sock_def_error_report(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk_has_sleeper(sk)) - wake_up_interruptible_poll(sk->sk_sleep, POLLERR); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_poll(&wq->wait, POLLERR); sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR); - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } static void sock_def_readable(struct sock *sk, int len) { - read_lock(&sk->sk_callback_lock); - if (sk_has_sleeper(sk)) - wake_up_interruptible_sync_poll(sk->sk_sleep, POLLIN | + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLRDNORM | POLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } static void sock_def_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { - if (sk_has_sleeper(sk)) - wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT | + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync_poll(&wq->wait, POLLOUT | POLLWRNORM | POLLWRBAND); /* Should agree with poll, otherwise some programs break */ @@ -1838,7 +1861,7 @@ static void sock_def_write_space(struct sock *sk) sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } static void sock_def_destruct(struct sock *sk) @@ -1885,7 +1908,6 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_allocation = GFP_KERNEL; sk->sk_rcvbuf = sysctl_rmem_default; sk->sk_sndbuf = sysctl_wmem_default; - sk->sk_backlog.limit = sk->sk_rcvbuf << 1; sk->sk_state = TCP_CLOSE; sk_set_socket(sk, sock); @@ -1893,12 +1915,12 @@ void sock_init_data(struct socket *sock, struct sock *sk) if (sock) { sk->sk_type = sock->type; - sk->sk_sleep = &sock->wait; + sk->sk_wq = sock->wq; sock->sk = sk; } else - sk->sk_sleep = NULL; + sk->sk_wq = NULL; - rwlock_init(&sk->sk_dst_lock); + spin_lock_init(&sk->sk_dst_lock); rwlock_init(&sk->sk_callback_lock); lockdep_set_class_and_name(&sk->sk_callback_lock, af_callback_keys + sk->sk_family, diff --git a/net/core/stream.c b/net/core/stream.c index a37debfeb1b..cc196f42b8d 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -28,15 +28,19 @@ void sk_stream_write_space(struct sock *sk) { struct socket *sock = sk->sk_socket; + struct socket_wq *wq; if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && sock) { clear_bit(SOCK_NOSPACE, &sock->flags); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_poll(sk->sk_sleep, POLLOUT | + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_poll(&wq->wait, POLLOUT | POLLWRNORM | POLLWRBAND); - if (sock->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) + if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT); + rcu_read_unlock(); } } @@ -66,13 +70,13 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p) if (signal_pending(tsk)) return sock_intr_errno(*timeo_p); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); sk->sk_write_pending++; done = sk_wait_event(sk, timeo_p, !sk->sk_err && !((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))); - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); sk->sk_write_pending--; } while (!done); return 0; @@ -96,13 +100,13 @@ void sk_stream_wait_close(struct sock *sk, long timeout) DEFINE_WAIT(wait); do { - prepare_to_wait(sk->sk_sleep, &wait, + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (sk_wait_event(sk, &timeout, !sk_stream_closing(sk))) break; } while (!signal_pending(current) && timeout); - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); } } @@ -126,7 +130,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) while (1) { set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; @@ -157,7 +161,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) *timeo_p = current_timeo; } out: - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return err; do_error: diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index b7b6b8208f7..01eee5d984b 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -11,12 +11,72 @@ #include <linux/socket.h> #include <linux/netdevice.h> #include <linux/ratelimit.h> +#include <linux/vmalloc.h> #include <linux/init.h> #include <linux/slab.h> #include <net/ip.h> #include <net/sock.h> +#ifdef CONFIG_RPS +static int rps_sock_flow_sysctl(ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + unsigned int orig_size, size; + int ret, i; + ctl_table tmp = { + .data = &size, + .maxlen = sizeof(size), + .mode = table->mode + }; + struct rps_sock_flow_table *orig_sock_table, *sock_table; + static DEFINE_MUTEX(sock_flow_mutex); + + mutex_lock(&sock_flow_mutex); + + orig_sock_table = rps_sock_flow_table; + size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0; + + ret = proc_dointvec(&tmp, write, buffer, lenp, ppos); + + if (write) { + if (size) { + if (size > 1<<30) { + /* Enforce limit to prevent overflow */ + mutex_unlock(&sock_flow_mutex); + return -EINVAL; + } + size = roundup_pow_of_two(size); + if (size != orig_size) { + sock_table = + vmalloc(RPS_SOCK_FLOW_TABLE_SIZE(size)); + if (!sock_table) { + mutex_unlock(&sock_flow_mutex); + return -ENOMEM; + } + + sock_table->mask = size - 1; + } else + sock_table = orig_sock_table; + + for (i = 0; i < size; i++) + sock_table->ents[i] = RPS_NO_CPU; + } else + sock_table = NULL; + + if (sock_table != orig_sock_table) { + rcu_assign_pointer(rps_sock_flow_table, sock_table); + synchronize_rcu(); + vfree(orig_sock_table); + } + } + + mutex_unlock(&sock_flow_mutex); + + return ret; +} +#endif /* CONFIG_RPS */ + static struct ctl_table net_core_table[] = { #ifdef CONFIG_NET { @@ -62,6 +122,13 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { + .procname = "netdev_tstamp_prequeue", + .data = &netdev_tstamp_prequeue, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { .procname = "message_cost", .data = &net_ratelimit_state.interval, .maxlen = sizeof(int), @@ -82,6 +149,14 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, +#ifdef CONFIG_RPS + { + .procname = "rps_sock_flow_entries", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = rps_sock_flow_sysctl + }, +#endif #endif /* CONFIG_NET */ { .procname = "netdev_budget", |