diff options
Diffstat (limited to 'net/core')
| -rw-r--r-- | net/core/datagram.c | 21 | ||||
| -rw-r--r-- | net/core/dev.c | 255 | ||||
| -rw-r--r-- | net/core/fib_rules.c | 2 | ||||
| -rw-r--r-- | net/core/filter.c | 7 | ||||
| -rw-r--r-- | net/core/net_namespace.c | 95 | ||||
| -rw-r--r-- | net/core/netpoll.c | 26 | ||||
| -rw-r--r-- | net/core/rtnetlink.c | 19 | ||||
| -rw-r--r-- | net/core/skbuff.c | 29 | ||||
| -rw-r--r-- | net/core/sock.c | 63 | ||||
| -rw-r--r-- | net/core/stream.c | 22 |
10 files changed, 312 insertions, 227 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c index 2dccd4ee591b..e0097531417a 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 b31d5d69a467..32611c8f1219 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1557,8 +1557,9 @@ static inline void __netif_reschedule(struct Qdisc *q) local_irq_save(flags); sd = &__get_cpu_var(softnet_data); - q->next_sched = sd->output_queue; - sd->output_queue = q; + q->next_sched = NULL; + *sd->output_queue_tailp = q; + sd->output_queue_tailp = &q->next_sched; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } @@ -1902,13 +1903,6 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, if (!list_empty(&ptype_all)) dev_queue_xmit_nit(skb, dev); - if (netif_needs_gso(dev, skb)) { - if (unlikely(dev_gso_segment(skb))) - goto out_kfree_skb; - if (skb->next) - goto gso; - } - /* * If device doesnt need skb->dst, release it right now while * its hot in this cpu cache @@ -1917,6 +1911,14 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, 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); @@ -1937,7 +1939,6 @@ gso: if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(nskb); - skb_orphan_try(nskb); rc = ops->ndo_start_xmit(nskb, dev); if (unlikely(rc != NETDEV_TX_OK)) { if (rc & ~NETDEV_TX_MASK) @@ -2015,8 +2016,12 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, if (dev->real_num_tx_queues > 1) queue_index = skb_tx_hash(dev, skb); - if (sk && rcu_dereference_check(sk->sk_dst_cache, 1)) - sk_tx_queue_set(sk, queue_index); + if (sk) { + 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); + } } } @@ -2200,7 +2205,13 @@ int netdev_max_backlog __read_mostly = 1000; 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 @@ -2225,7 +2236,11 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, int cpu = -1; u8 ip_proto; u16 tcpu; - u32 addr1, addr2, ports, ihl; + u32 addr1, addr2, ihl; + union { + u32 v32; + u16 v16[2]; + } ports; if (skb_rx_queue_recorded(skb)) { u16 index = skb_get_rx_queue(skb); @@ -2271,7 +2286,6 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, default: goto done; } - ports = 0; switch (ip_proto) { case IPPROTO_TCP: case IPPROTO_UDP: @@ -2281,25 +2295,20 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, case IPPROTO_SCTP: case IPPROTO_UDPLITE: if (pskb_may_pull(skb, (ihl * 4) + 4)) { - __be16 *hports = (__be16 *) (skb->data + (ihl * 4)); - u32 sport, dport; - - sport = (__force u16) hports[0]; - dport = (__force u16) hports[1]; - if (dport < sport) - swap(sport, dport); - ports = (sport << 16) + dport; + ports.v32 = * (__force u32 *) (skb->data + (ihl * 4)); + if (ports.v16[1] < ports.v16[0]) + swap(ports.v16[0], ports.v16[1]); + break; } - 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, hashrnd); + skb->rxhash = jhash_3words(addr1, addr2, ports.v32, hashrnd); if (!skb->rxhash) skb->rxhash = 1; @@ -2362,8 +2371,8 @@ static void rps_trigger_softirq(void *data) { struct softnet_data *sd = data; - __napi_schedule(&sd->backlog); - __get_cpu_var(netdev_rx_stat).received_rps++; + ____napi_schedule(sd, &sd->backlog); + sd->received_rps++; } #endif /* CONFIG_RPS */ @@ -2402,15 +2411,15 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, sd = &per_cpu(softnet_data, cpu); local_irq_save(flags); - __get_cpu_var(netdev_rx_stat).total++; rps_lock(sd); - if (sd->input_pkt_queue.qlen <= netdev_max_backlog) { - if (sd->input_pkt_queue.qlen) { + 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 + sd->input_pkt_queue.qlen; + *qtail = sd->input_queue_head + + skb_queue_len(&sd->input_pkt_queue); #endif rps_unlock(sd); local_irq_restore(flags); @@ -2420,14 +2429,14 @@ enqueue: /* Schedule NAPI for backlog device */ if (napi_schedule_prep(&sd->backlog)) { if (!rps_ipi_queued(sd)) - __napi_schedule(&sd->backlog); + ____napi_schedule(sd, &sd->backlog); } goto enqueue; } + sd->dropped++; rps_unlock(sd); - __get_cpu_var(netdev_rx_stat).dropped++; local_irq_restore(flags); kfree_skb(skb); @@ -2527,6 +2536,7 @@ 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) { @@ -2801,7 +2811,7 @@ static 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); @@ -2930,13 +2940,21 @@ static void flush_backlog(void *arg) struct sk_buff *skb, *tmp; rps_lock(sd); - skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) + skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev == dev) { __skb_unlink(skb, &sd->input_pkt_queue); kfree_skb(skb); - input_queue_head_incr(sd); + 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) @@ -3239,30 +3257,85 @@ 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 *sd = &__get_cpu_var(softnet_data); + 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(); - rps_lock(sd); - skb = __skb_dequeue(&sd->input_pkt_queue); - if (!skb) { - __napi_complete(napi); - rps_unlock(sd); + while ((skb = __skb_dequeue(&sd->process_queue))) { local_irq_enable(); - break; + __netif_receive_skb(skb); + if (++work >= quota) + return work; + local_irq_disable(); } - input_queue_head_incr(sd); - rps_unlock(sd); - local_irq_enable(); - __netif_receive_skb(skb); - } while (++work < quota); + 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; } @@ -3278,8 +3351,7 @@ 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); @@ -3350,45 +3422,16 @@ void netif_napi_del(struct napi_struct *napi) } EXPORT_SYMBOL(netif_napi_del); -/* - * 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_disable(void) -{ -#ifdef CONFIG_RPS - struct softnet_data *sd = &__get_cpu_var(softnet_data); - 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 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; @@ -3406,7 +3449,7 @@ 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); @@ -3441,13 +3484,13 @@ 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: - net_rps_action_and_irq_disable(); + net_rps_action_and_irq_enable(sd); #ifdef CONFIG_NET_DMA /* @@ -3460,7 +3503,7 @@ out: return; softnet_break: - __get_cpu_var(netdev_rx_stat).time_squeeze++; + sd->time_squeeze++; __raise_softirq_irqoff(NET_RX_SOFTIRQ); goto out; } @@ -3661,17 +3704,17 @@ 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) @@ -3691,12 +3734,12 @@ 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 %08x\n", - s->total, s->dropped, s->time_squeeze, 0, + sd->processed, sd->dropped, sd->time_squeeze, 0, 0, 0, 0, 0, /* was fastroute */ - s->cpu_collision, s->received_rps); + sd->cpu_collision, sd->received_rps); return 0; } @@ -5584,7 +5627,6 @@ 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; @@ -5605,13 +5647,13 @@ 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(); @@ -5619,8 +5661,10 @@ static int dev_cpu_callback(struct notifier_block *nfb, /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); - input_queue_head_incr(oldsd); + input_queue_head_add(oldsd, 1); } + while ((skb = __skb_dequeue(&oldsd->process_queue))) + netif_rx(skb); return NOTIFY_OK; } @@ -5838,10 +5882,13 @@ static int __init net_dev_init(void) for_each_possible_cpu(i) { struct softnet_data *sd = &per_cpu(softnet_data, i); + 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; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 1bc66592453c..42e84e08a1be 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -122,7 +122,7 @@ 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; diff --git a/net/core/filter.c b/net/core/filter.c index ff943bed21af..da69fb728d32 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/net_namespace.c b/net/core/net_namespace.c index bd8c4712ea24..c988e685433a 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 a58f59b97597..94825b109551 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/rtnetlink.c b/net/core/rtnetlink.c index 78c85985cb30..23a71cb21273 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 +118,7 @@ static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex) { struct rtnl_link *tab; - if (protocol < NPROTO) + if (protocol <= RTNL_FAMILY_MAX) tab = rtnl_msg_handlers[protocol]; else tab = NULL; @@ -133,7 +133,7 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) { struct rtnl_link *tab; - if (protocol < NPROTO) + if (protocol <= RTNL_FAMILY_MAX) tab = rtnl_msg_handlers[protocol]; else tab = NULL; @@ -167,7 +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]; @@ -219,7 +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) @@ -241,7 +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; @@ -1319,10 +1319,11 @@ replay: err = ops->newlink(net, dev, tb, data); else err = register_netdevice(dev); - if (err < 0 && !IS_ERR(dev)) { + + if (err < 0 && !IS_ERR(dev)) free_netdev(dev); + if (err < 0) goto out; - } err = rtnl_configure_link(dev, ifm); if (err < 0) @@ -1384,7 +1385,7 @@ 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; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index bdea0efdf8cb..a9b0e1f77806 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; @@ -1053,7 +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 7effa1e689df..94c4affdda9b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -327,6 +327,10 @@ 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 @@ -1207,7 +1211,7 @@ 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); @@ -1395,7 +1399,7 @@ 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 +1408,7 @@ 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; } @@ -1570,11 +1574,11 @@ 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 +1800,53 @@ 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 +1854,7 @@ 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 +1901,6 @@ 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); @@ -1893,10 +1908,10 @@ 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; spin_lock_init(&sk->sk_dst_lock); rwlock_init(&sk->sk_callback_lock); diff --git a/net/core/stream.c b/net/core/stream.c index a37debfeb1b2..cc196f42b8d8 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: |