diff options
Diffstat (limited to 'net')
34 files changed, 749 insertions, 163 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 453512266ea1..c39a5f41169c 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -530,6 +530,10 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, } unregister_netdevice_many(&list); break; + + case NETDEV_PRE_TYPE_CHANGE: + /* Forbid underlaying device to change its type. */ + return NOTIFY_BAD; } out: diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c index b6234b73c4cf..326ab453edb7 100644 --- a/net/bluetooth/bnep/netdev.c +++ b/net/bluetooth/bnep/netdev.c @@ -87,7 +87,7 @@ static void bnep_net_set_mc_list(struct net_device *dev) memcpy(__skb_put(skb, ETH_ALEN), dev->broadcast, ETH_ALEN); r->len = htons(ETH_ALEN * 2); } else { - struct dev_mc_list *dmi = dev->mc_list; + struct dev_mc_list *dmi; int i, len = skb->len; if (dev->flags & IFF_BROADCAST) { @@ -97,12 +97,12 @@ static void bnep_net_set_mc_list(struct net_device *dev) /* FIXME: We should group addresses here. */ - for (i = 0; - i < netdev_mc_count(dev) && i < BNEP_MAX_MULTICAST_FILTERS; - i++) { + i = 0; + netdev_for_each_mc_addr(dmi, dev) { + if (i == BNEP_MAX_MULTICAST_FILTERS) + break; memcpy(__skb_put(skb, ETH_ALEN), dmi->dmi_addr, ETH_ALEN); memcpy(__skb_put(skb, ETH_ALEN), dmi->dmi_addr, ETH_ALEN); - dmi = dmi->next; } r->len = htons(skb->len - len); } diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 90a9024e5c1e..5b8a6e73b02f 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -26,11 +26,12 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) const unsigned char *dest = skb->data; struct net_bridge_fdb_entry *dst; struct net_bridge_mdb_entry *mdst; + struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats); - BR_INPUT_SKB_CB(skb)->brdev = dev; + brstats->tx_packets++; + brstats->tx_bytes += skb->len; - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; + BR_INPUT_SKB_CB(skb)->brdev = dev; skb_reset_mac_header(skb); skb_pull(skb, ETH_HLEN); @@ -81,6 +82,31 @@ static int br_dev_stop(struct net_device *dev) return 0; } +static struct net_device_stats *br_get_stats(struct net_device *dev) +{ + struct net_bridge *br = netdev_priv(dev); + struct net_device_stats *stats = &dev->stats; + struct br_cpu_netstats sum = { 0 }; + unsigned int cpu; + + for_each_possible_cpu(cpu) { + const struct br_cpu_netstats *bstats + = per_cpu_ptr(br->stats, cpu); + + sum.tx_bytes += bstats->tx_bytes; + sum.tx_packets += bstats->tx_packets; + sum.rx_bytes += bstats->rx_bytes; + sum.rx_packets += bstats->rx_packets; + } + + stats->tx_bytes = sum.tx_bytes; + stats->tx_packets = sum.tx_packets; + stats->rx_bytes = sum.rx_bytes; + stats->rx_packets = sum.rx_packets; + + return stats; +} + static int br_change_mtu(struct net_device *dev, int new_mtu) { struct net_bridge *br = netdev_priv(dev); @@ -180,19 +206,28 @@ static const struct net_device_ops br_netdev_ops = { .ndo_open = br_dev_open, .ndo_stop = br_dev_stop, .ndo_start_xmit = br_dev_xmit, + .ndo_get_stats = br_get_stats, .ndo_set_mac_address = br_set_mac_address, .ndo_set_multicast_list = br_dev_set_multicast_list, .ndo_change_mtu = br_change_mtu, .ndo_do_ioctl = br_dev_ioctl, }; +static void br_dev_free(struct net_device *dev) +{ + struct net_bridge *br = netdev_priv(dev); + + free_percpu(br->stats); + free_netdev(dev); +} + void br_dev_setup(struct net_device *dev) { random_ether_addr(dev->dev_addr); ether_setup(dev); dev->netdev_ops = &br_netdev_ops; - dev->destructor = free_netdev; + dev->destructor = br_dev_free; SET_ETHTOOL_OPS(dev, &br_ethtool_ops); dev->tx_queue_len = 0; dev->priv_flags = IFF_EBRIDGE; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index b6a3872f5681..b7cdd2e98050 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -185,6 +185,12 @@ static struct net_device *new_bridge_dev(struct net *net, const char *name) br = netdev_priv(dev); br->dev = dev; + br->stats = alloc_percpu(struct br_cpu_netstats); + if (!br->stats) { + free_netdev(dev); + return NULL; + } + spin_lock_init(&br->lock); INIT_LIST_HEAD(&br->port_list); spin_lock_init(&br->hash_lock); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index d74d570fc848..333dfb7c5886 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -23,9 +23,11 @@ const u8 br_group_address[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; static int br_pass_frame_up(struct sk_buff *skb) { struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; + struct net_bridge *br = netdev_priv(brdev); + struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats); - brdev->stats.rx_packets++; - brdev->stats.rx_bytes += skb->len; + brstats->rx_packets++; + brstats->rx_bytes += skb->len; indev = skb->dev; skb->dev = brdev; diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c index 763a3ec292e5..1413b72acc7f 100644 --- a/net/bridge/br_notify.c +++ b/net/bridge/br_notify.c @@ -82,6 +82,10 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v case NETDEV_UNREGISTER: br_del_if(br, dev); break; + + case NETDEV_PRE_TYPE_CHANGE: + /* Forbid underlaying device to change its type. */ + return NOTIFY_BAD; } /* Events that may cause spanning tree to refresh */ diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 846d7d1e2075..791d4ab0fd4d 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -135,6 +135,14 @@ struct net_bridge spinlock_t lock; struct list_head port_list; struct net_device *dev; + + struct br_cpu_netstats __percpu { + unsigned long rx_packets; + unsigned long rx_bytes; + unsigned long tx_packets; + unsigned long tx_bytes; + } *stats; + spinlock_t hash_lock; struct hlist_head hash[BR_HASH_SIZE]; unsigned long feature_mask; diff --git a/net/core/dev.c b/net/core/dev.c index 59d4394d2ce8..c0e260870c0a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1084,9 +1084,9 @@ 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); @@ -1931,7 +1931,7 @@ 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) { @@ -1949,7 +1949,7 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) else hash = 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 +1959,9 @@ 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 " + netdev_warn(dev, "selects TX queue %d, but " "real number of TX queues is %d\n", - dev->name, queue_index, - dev->real_num_tx_queues); + queue_index, dev->real_num_tx_queues); } return 0; } @@ -2175,6 +2174,178 @@ int weight_p __read_mostly = 64; /* old backlog weight */ DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, }; +#ifdef CONFIG_SMP +/* + * 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. + */ +static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb) +{ + struct ipv6hdr *ip6; + struct iphdr *ip; + struct netdev_rx_queue *rxqueue; + struct rps_map *map; + int cpu = -1; + u8 ip_proto; + u32 addr1, addr2, ports, ihl; + + rcu_read_lock(); + + if (skb_rx_queue_recorded(skb)) { + u16 index = skb_get_rx_queue(skb); + if (unlikely(index >= dev->num_rx_queues)) { + if (net_ratelimit()) { + netdev_warn(dev, "received packet on queue " + "%u, but number of RX queues is %u\n", + index, dev->num_rx_queues); + } + goto done; + } + rxqueue = dev->_rx + index; + } else + rxqueue = dev->_rx; + + if (!rxqueue->rps_map) + 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 = ip->saddr; + addr2 = 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 = ip6->saddr.s6_addr32[3]; + addr2 = ip6->daddr.s6_addr32[3]; + ihl = (40 >> 2); + break; + default: + goto done; + } + ports = 0; + 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 = *((u32 *) (skb->data + (ihl * 4))); + break; + + default: + break; + } + + skb->rxhash = jhash_3words(addr1, addr2, ports, hashrnd); + if (!skb->rxhash) + skb->rxhash = 1; + +got_hash: + map = rcu_dereference(rxqueue->rps_map); + if (map) { + u16 tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32]; + + if (cpu_online(tcpu)) { + cpu = tcpu; + goto done; + } + } + +done: + rcu_read_unlock(); + return cpu; +} + +/* + * This structure holds the per-CPU mask of CPUs for which IPIs are scheduled + * to be sent to kick remote softirq processing. There are two masks since + * the sending of IPIs must be done with interrupts enabled. The select field + * indicates the current mask that enqueue_backlog uses to schedule IPIs. + * select is flipped before net_rps_action is called while still under lock, + * net_rps_action then uses the non-selected mask to send the IPIs and clears + * it without conflicting with enqueue_backlog operation. + */ +struct rps_remote_softirq_cpus { + cpumask_t mask[2]; + int select; +}; +static DEFINE_PER_CPU(struct rps_remote_softirq_cpus, rps_remote_softirq_cpus); + +/* Called from hardirq (IPI) context */ +static void trigger_softirq(void *data) +{ + struct softnet_data *queue = data; + __napi_schedule(&queue->backlog); + __get_cpu_var(netdev_rx_stat).received_rps++; +} +#endif /* CONFIG_SMP */ + +/* + * 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) +{ + struct softnet_data *queue; + unsigned long flags; + + queue = &per_cpu(softnet_data, cpu); + + local_irq_save(flags); + __get_cpu_var(netdev_rx_stat).total++; + + spin_lock(&queue->input_pkt_queue.lock); + if (queue->input_pkt_queue.qlen <= netdev_max_backlog) { + if (queue->input_pkt_queue.qlen) { +enqueue: + __skb_queue_tail(&queue->input_pkt_queue, skb); + spin_unlock_irqrestore(&queue->input_pkt_queue.lock, + flags); + return NET_RX_SUCCESS; + } + + /* Schedule NAPI for backlog device */ + if (napi_schedule_prep(&queue->backlog)) { +#ifdef CONFIG_SMP + if (cpu != smp_processor_id()) { + struct rps_remote_softirq_cpus *rcpus = + &__get_cpu_var(rps_remote_softirq_cpus); + + cpu_set(cpu, rcpus->mask[rcpus->select]); + __raise_softirq_irqoff(NET_RX_SOFTIRQ); + } else + __napi_schedule(&queue->backlog); +#else + __napi_schedule(&queue->backlog); +#endif + } + goto enqueue; + } + + spin_unlock(&queue->input_pkt_queue.lock); + + __get_cpu_var(netdev_rx_stat).dropped++; + local_irq_restore(flags); + + kfree_skb(skb); + return NET_RX_DROP; +} /** * netif_rx - post buffer to the network code @@ -2193,8 +2364,7 @@ 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 cpu; /* if netpoll wants it, pretend we never saw it */ if (netpoll_rx(skb)) @@ -2203,31 +2373,15 @@ int netif_rx(struct sk_buff *skb) if (!skb->tstamp.tv64) net_timestamp(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); - - __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; - } - - napi_schedule(&queue->backlog); - goto enqueue; - } - - __get_cpu_var(netdev_rx_stat).dropped++; - local_irq_restore(flags); +#ifdef CONFIG_SMP + cpu = get_rps_cpu(skb->dev, skb); + if (cpu < 0) + cpu = smp_processor_id(); +#else + cpu = smp_processor_id(); +#endif - kfree_skb(skb); - return NET_RX_DROP; + return enqueue_to_backlog(skb, cpu); } EXPORT_SYMBOL(netif_rx); @@ -2464,22 +2618,7 @@ 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 - */ -int netif_receive_skb(struct sk_buff *skb) +int __netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; struct net_device *orig_dev; @@ -2590,6 +2729,37 @@ 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) +{ +#ifdef CONFIG_SMP + int cpu; + + cpu = get_rps_cpu(skb->dev, skb); + + if (cpu < 0) + return __netif_receive_skb(skb); + else + return enqueue_to_backlog(skb, cpu); +#else + return __netif_receive_skb(skb); +#endif +} EXPORT_SYMBOL(netif_receive_skb); /* Network device is going away, flush any packets still pending */ @@ -2916,16 +3086,16 @@ static int process_backlog(struct napi_struct *napi, int quota) do { struct sk_buff *skb; - local_irq_disable(); + spin_lock_irq(&queue->input_pkt_queue.lock); skb = __skb_dequeue(&queue->input_pkt_queue); if (!skb) { __napi_complete(napi); - local_irq_enable(); + spin_unlock_irq(&queue->input_pkt_queue.lock); break; } - local_irq_enable(); + spin_unlock_irq(&queue->input_pkt_queue.lock); - netif_receive_skb(skb); + __netif_receive_skb(skb); } while (++work < quota && jiffies == start_time); return work; @@ -3014,6 +3184,24 @@ void netif_napi_del(struct napi_struct *napi) } EXPORT_SYMBOL(netif_napi_del); +#ifdef CONFIG_SMP +/* + * net_rps_action sends any pending IPI's for rps. This is only called from + * softirq and interrupts must be enabled. + */ +static void net_rps_action(cpumask_t *mask) +{ + int cpu; + + /* Send pending IPI's to kick RPS processing on remote cpus. */ + for_each_cpu_mask_nr(cpu, *mask) { + struct softnet_data *queue = &per_cpu(softnet_data, cpu); + if (cpu_online(cpu)) + __smp_call_function_single(cpu, &queue->csd, 0); + } + cpus_clear(*mask); +} +#endif static void net_rx_action(struct softirq_action *h) { @@ -3021,6 +3209,10 @@ static void net_rx_action(struct softirq_action *h) unsigned long time_limit = jiffies + 2; int budget = netdev_budget; void *have; +#ifdef CONFIG_SMP + int select; + struct rps_remote_softirq_cpus *rcpus; +#endif local_irq_disable(); @@ -3083,8 +3275,18 @@ static void net_rx_action(struct softirq_action *h) netpoll_poll_unlock(have); } out: +#ifdef CONFIG_SMP + rcpus = &__get_cpu_var(rps_remote_softirq_cpus); + select = rcpus->select; + rcpus->select ^= 1; + local_irq_enable(); + net_rps_action(&rcpus->mask[select]); +#else + local_irq_enable(); +#endif + #ifdef CONFIG_NET_DMA /* * There may not be any more sk_buffs coming right now, so push @@ -3329,10 +3531,10 @@ static int softnet_seq_show(struct seq_file *seq, void *v) { struct netif_rx_stats *s = v; - seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n", + seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", s->total, s->dropped, s->time_squeeze, 0, 0, 0, 0, 0, /* was fastroute */ - s->cpu_collision); + s->cpu_collision, s->received_rps); return 0; } @@ -5069,6 +5271,23 @@ int register_netdevice(struct net_device *dev) dev->iflink = -1; + 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; + } + /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); @@ -5426,9 +5645,11 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, void (*setup)(struct net_device *), unsigned int queue_count) { struct netdev_queue *tx; + struct netdev_rx_queue *rx; struct net_device *dev; size_t alloc_size; struct net_device *p; + int i; BUG_ON(strlen(name) >= sizeof(dev->name)); @@ -5454,11 +5675,27 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, goto free_p; } + 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; + 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); @@ -5468,6 +5705,9 @@ 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; + dev->_rx = rx; + dev->num_rx_queues = queue_count; + dev->gso_max_size = GSO_MAX_SIZE; netdev_init_queues(dev); @@ -5482,9 +5722,10 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, strcpy(dev->name, name); return dev; +free_rx: + kfree(rx); free_tx: kfree(tx); - free_p: kfree(p); return NULL; @@ -5987,6 +6228,12 @@ static int __init net_dev_init(void) queue->completion_queue = NULL; INIT_LIST_HEAD(&queue->poll_list); +#ifdef CONFIG_SMP + queue->csd.func = trigger_softirq; + queue->csd.info = queue; + queue->csd.flags = 0; +#endif + queue->backlog.poll = process_backlog; queue->backlog.weight = weight_p; queue->backlog.gro_list = NULL; @@ -6025,7 +6272,7 @@ 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/fib_rules.c b/net/core/fib_rules.c index 9a24377146bf..2ff34894357a 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -108,7 +108,7 @@ fib_rules_register(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); @@ -123,7 +123,6 @@ 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) @@ -157,7 +156,6 @@ 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, @@ -220,7 +218,6 @@ out: return err; } - EXPORT_SYMBOL_GPL(fib_rules_lookup); static int validate_rulemsg(struct fib_rule_hdr *frh, struct nlattr **tb, @@ -613,7 +610,7 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) break; cb->args[1] = 0; - skip: +skip: idx++; } rcu_read_unlock(); @@ -685,7 +682,6 @@ 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: @@ -699,8 +695,6 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event, break; } - rcu_read_unlock(); - return NOTIFY_DONE; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 099c753c4213..7a46343d5ae3 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -466,6 +466,216 @@ static struct attribute_group wireless_group = { }; #endif +/* + * 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); +} + +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 struct rx_queue_attribute rps_cpus_attribute = + __ATTR(rps_cpus, S_IRUGO | S_IWUSR, show_rps_map, store_rps_map); + +static struct attribute *rx_queue_default_attrs[] = { + &rps_cpus_attribute.attr, + NULL +}; + +static void rx_queue_release(struct kobject *kobj) +{ + struct netdev_rx_queue *queue = to_rx_queue(kobj); + struct rps_map *map = queue->rps_map; + struct netdev_rx_queue *first = queue->first; + + if (map) + call_rcu(&map->rcu, rps_map_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_SYSFS */ #ifdef CONFIG_HOTPLUG @@ -529,6 +739,8 @@ void netdev_unregister_kobject(struct net_device * net) if (!net_eq(dev_net(net), &init_net)) return; + rx_queue_remove_kobjects(net); + device_del(dev); } @@ -537,6 +749,7 @@ 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; @@ -563,7 +776,17 @@ 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; + + error = rx_queue_register_kobjects(net); + if (error) { + device_del(dev); + return error; + } + + return error; } int netdev_class_create_file(struct class_attribute *class_attr) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 4568120d8533..e1121f0bca6a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -600,7 +600,39 @@ 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(struct rtnl_link_stats64 *a, + const struct net_device_stats *b) +{ + 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; +} static inline int rtnl_vfinfo_size(const struct net_device *dev) { @@ -698,6 +730,14 @@ 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; + + stats = dev_get_stats(dev); + copy_rtnl_link_stats64(nla_data(attr), stats); + if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) { int i; struct ifla_vf_info ivi; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 93c4e060c91e..bdea0efdf8cb 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -534,6 +534,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->network_header = old->network_header; new->mac_header = old->mac_header; skb_dst_set(new, dst_clone(skb_dst(old))); + new->rxhash = old->rxhash; #ifdef CONFIG_XFRM new->sp = secpath_get(old->sp); #endif @@ -581,6 +582,7 @@ 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; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 0c94a1ac2946..c9a1c68767ff 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -587,9 +587,15 @@ choice config DEFAULT_HTCP bool "Htcp" if TCP_CONG_HTCP=y + config DEFAULT_HYBLA + bool "Hybla" if TCP_CONG_HYBLA=y + config DEFAULT_VEGAS bool "Vegas" if TCP_CONG_VEGAS=y + config DEFAULT_VENO + bool "Veno" if TCP_CONG_VENO=y + config DEFAULT_WESTWOOD bool "Westwood" if TCP_CONG_WESTWOOD=y @@ -610,8 +616,10 @@ config DEFAULT_TCP_CONG default "bic" if DEFAULT_BIC default "cubic" if DEFAULT_CUBIC default "htcp" if DEFAULT_HTCP + default "hybla" if DEFAULT_HYBLA default "vegas" if DEFAULT_VEGAS default "westwood" if DEFAULT_WESTWOOD + default "veno" if DEFAULT_VENO default "reno" if DEFAULT_RENO default "cubic" diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 51ca946e3392..c75320ef95c2 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1095,10 +1095,10 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, case NETDEV_DOWN: ip_mc_down(in_dev); break; - case NETDEV_BONDING_OLDTYPE: + case NETDEV_PRE_TYPE_CHANGE: ip_mc_unmap(in_dev); break; - case NETDEV_BONDING_NEWTYPE: + case NETDEV_POST_TYPE_CHANGE: ip_mc_remap(in_dev); break; case NETDEV_CHANGEMTU: diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3381b4317c27..8d41abc40db5 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -137,8 +137,8 @@ static DEFINE_SPINLOCK(addrconf_verify_lock); static void addrconf_join_anycast(struct inet6_ifaddr *ifp); static void addrconf_leave_anycast(struct inet6_ifaddr *ifp); -static void addrconf_bonding_change(struct net_device *dev, - unsigned long event); +static void addrconf_type_change(struct net_device *dev, + unsigned long event); static int addrconf_ifdown(struct net_device *dev, int how); static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags); @@ -2584,9 +2584,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, return notifier_from_errno(err); } break; - case NETDEV_BONDING_OLDTYPE: - case NETDEV_BONDING_NEWTYPE: - addrconf_bonding_change(dev, event); + case NETDEV_PRE_TYPE_CHANGE: + case NETDEV_POST_TYPE_CHANGE: + addrconf_type_change(dev, event); break; } @@ -2601,16 +2601,16 @@ static struct notifier_block ipv6_dev_notf = { .priority = 0 }; -static void addrconf_bonding_change(struct net_device *dev, unsigned long event) +static void addrconf_type_change(struct net_device *dev, unsigned long event) { struct inet6_dev *idev; ASSERT_RTNL(); idev = __in6_dev_get(dev); - if (event == NETDEV_BONDING_NEWTYPE) + if (event == NETDEV_POST_TYPE_CHANGE) ipv6_mc_remap(idev); - else if (event == NETDEV_BONDING_OLDTYPE) + else if (event == NETDEV_PRE_TYPE_CHANGE) ipv6_mc_unmap(idev); } diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 853c52be781f..937ecda4abe7 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -159,7 +159,8 @@ static unsigned int rds_poll(struct file *file, struct socket *sock, poll_wait(file, sk->sk_sleep, wait); - poll_wait(file, &rds_poll_waitq, wait); + if (rs->rs_seen_congestion) + poll_wait(file, &rds_poll_waitq, wait); read_lock_irqsave(&rs->rs_recv_lock, flags); if (!rs->rs_cong_monitor) { @@ -181,6 +182,10 @@ static unsigned int rds_poll(struct file *file, struct socket *sock, mask |= (POLLOUT | POLLWRNORM); read_unlock_irqrestore(&rs->rs_recv_lock, flags); + /* clear state any time we wake a seen-congested socket */ + if (mask) + rs->rs_seen_congestion = 0; + return mask; } diff --git a/net/rds/cong.c b/net/rds/cong.c index 6d06cac2649c..dd2711df640b 100644 --- a/net/rds/cong.c +++ b/net/rds/cong.c @@ -218,8 +218,6 @@ void rds_cong_queue_updates(struct rds_cong_map *map) spin_lock_irqsave(&rds_cong_lock, flags); list_for_each_entry(conn, &map->m_conn_list, c_map_item) { - if (conn->c_loopback) - continue; if (!test_and_set_bit(0, &conn->c_map_queued)) { rds_stats_inc(s_cong_update_queued); queue_delayed_work(rds_wq, &conn->c_send_w, 0); diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 647cb8ffc39b..e1f124bf03bb 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -203,9 +203,10 @@ static void rds_ib_qp_event_handler(struct ib_event *event, void *data) rdma_notify(ic->i_cm_id, IB_EVENT_COMM_EST); break; default: - rds_ib_conn_error(conn, "RDS/IB: Fatal QP Event %u " + rdsdebug("Fatal QP Event %u " "- connection %pI4->%pI4, reconnecting\n", event->event, &conn->c_laddr, &conn->c_faddr); + rds_conn_drop(conn); break; } } diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 4b0da865a72c..cfb1d904ed00 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -234,8 +234,8 @@ void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *pool) { flush_workqueue(rds_wq); rds_ib_flush_mr_pool(pool, 1); - BUG_ON(atomic_read(&pool->item_count)); - BUG_ON(atomic_read(&pool->free_pinned)); + WARN_ON(atomic_read(&pool->item_count)); + WARN_ON(atomic_read(&pool->free_pinned)); kfree(pool); } @@ -440,6 +440,7 @@ static void __rds_ib_teardown_mr(struct rds_ib_mr *ibmr) /* FIXME we need a way to tell a r/w MR * from a r/o MR */ + BUG_ON(in_interrupt()); set_page_dirty(page); put_page(page); } diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 04dc0d3f3c95..c338881eca71 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -468,8 +468,8 @@ static void rds_ib_send_ack(struct rds_ib_connection *ic, unsigned int adv_credi set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags); rds_ib_stats_inc(s_ib_ack_send_failure); - /* Need to finesse this later. */ - BUG(); + + rds_ib_conn_error(ic->conn, "sending ack failed\n"); } else rds_ib_stats_inc(s_ib_ack_sent); } diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index a10fab6886d1..17fa80803ab0 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -243,8 +243,12 @@ void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context) struct rds_message *rm; rm = rds_send_get_message(conn, send->s_op); - if (rm) + if (rm) { + if (rm->m_rdma_op) + rds_ib_send_unmap_rdma(ic, rm->m_rdma_op); rds_ib_send_rdma_complete(rm, wc.status); + rds_message_put(rm); + } } oldest = (oldest + 1) % ic->i_send_ring.w_nr; @@ -482,6 +486,13 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, BUG_ON(off % RDS_FRAG_SIZE); BUG_ON(hdr_off != 0 && hdr_off != sizeof(struct rds_header)); + /* Do not send cong updates to IB loopback */ + if (conn->c_loopback + && rm->m_inc.i_hdr.h_flags & RDS_FLAG_CONG_BITMAP) { + rds_cong_map_updated(conn->c_fcong, ~(u64) 0); + return sizeof(struct rds_header) + RDS_CONG_MAP_BYTES; + } + /* FIXME we may overallocate here */ if (be32_to_cpu(rm->m_inc.i_hdr.h_len) == 0) i = 1; @@ -574,8 +585,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, rds_ib_send_grab_credits(ic, 0, &posted, 1, RDS_MAX_ADV_CREDIT - adv_credits); adv_credits += posted; BUG_ON(adv_credits > 255); - } else if (ic->i_rm != rm) - BUG(); + } send = &ic->i_sends[pos]; first = send; @@ -714,8 +724,8 @@ add_header: ic->i_rm = prev->s_rm; prev->s_rm = NULL; } - /* Finesse this later */ - BUG(); + + rds_ib_conn_error(ic->conn, "ib_post_send failed\n"); goto out; } diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c index 394cf6b4d0aa..6bc638fd252c 100644 --- a/net/rds/iw_cm.c +++ b/net/rds/iw_cm.c @@ -156,9 +156,11 @@ static void rds_iw_qp_event_handler(struct ib_event *event, void *data) case IB_EVENT_QP_REQ_ERR: case IB_EVENT_QP_FATAL: default: - rds_iw_conn_error(conn, "RDS/IW: Fatal QP Event %u - connection %pI4->%pI4...reconnecting\n", + rdsdebug("Fatal QP Event %u " + "- connection %pI4->%pI4, reconnecting\n", event->event, &conn->c_laddr, &conn->c_faddr); + rds_conn_drop(conn); break; } } diff --git a/net/rds/iw_recv.c b/net/rds/iw_recv.c index 54af7d6b92da..337e4e5025e2 100644 --- a/net/rds/iw_recv.c +++ b/net/rds/iw_recv.c @@ -468,8 +468,8 @@ static void rds_iw_send_ack(struct rds_iw_connection *ic, unsigned int adv_credi set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags); rds_iw_stats_inc(s_iw_ack_send_failure); - /* Need to finesse this later. */ - BUG(); + + rds_iw_conn_error(ic->conn, "sending ack failed\n"); } else rds_iw_stats_inc(s_iw_ack_sent); } diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c index 1379e9d66a78..52182ff7519e 100644 --- a/net/rds/iw_send.c +++ b/net/rds/iw_send.c @@ -616,8 +616,7 @@ int rds_iw_xmit(struct rds_connection *conn, struct rds_message *rm, rds_iw_send_grab_credits(ic, 0, &posted, 1, RDS_MAX_ADV_CREDIT - adv_credits); adv_credits += posted; BUG_ON(adv_credits > 255); - } else if (ic->i_rm != rm) - BUG(); + } send = &ic->i_sends[pos]; first = send; diff --git a/net/rds/loop.c b/net/rds/loop.c index 4a61997f554d..93a45f1ce61f 100644 --- a/net/rds/loop.c +++ b/net/rds/loop.c @@ -80,16 +80,9 @@ static int rds_loop_xmit_cong_map(struct rds_connection *conn, struct rds_cong_map *map, unsigned long offset) { - unsigned long i; - BUG_ON(offset); BUG_ON(map != conn->c_lcong); - for (i = 0; i < RDS_CONG_MAP_PAGES; i++) { - memcpy((void *)conn->c_fcong->m_page_addrs[i], - (void *)map->m_page_addrs[i], PAGE_SIZE); - } - rds_cong_map_updated(conn->c_fcong, ~(u64) 0); return sizeof(struct rds_header) + RDS_CONG_MAP_BYTES; diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 4c64daa1f5d5..61b359d9dffd 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -438,8 +438,10 @@ void rds_rdma_free_op(struct rds_rdma_op *ro) /* Mark page dirty if it was possibly modified, which * is the case for a RDMA_READ which copies from remote * to local memory */ - if (!ro->r_write) + if (!ro->r_write) { + BUG_ON(in_interrupt()); set_page_dirty(page); + } put_page(page); } diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index 9ece910ea394..5ea82fc47c3e 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -101,7 +101,7 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_DISCONNECTED: - printk(KERN_WARNING "RDS/RDMA: DISCONNECT event - dropping connection " + rdsdebug("DISCONNECT event - dropping connection " "%pI4->%pI4\n", &conn->c_laddr, &conn->c_faddr); rds_conn_drop(conn); @@ -109,8 +109,7 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, default: /* things like device disconnect? */ - printk(KERN_ERR "unknown event %u\n", event->event); - BUG(); + printk(KERN_ERR "RDS: unknown event %u!\n", event->event); break; } diff --git a/net/rds/rds.h b/net/rds/rds.h index 85d6f897ecc7..4bec6e2ed495 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -388,6 +388,8 @@ struct rds_sock { /* flag indicating we were congested or not */ int rs_congested; + /* seen congestion (ENOBUFS) when sending? */ + int rs_seen_congestion; /* rs_lock protects all these adjacent members before the newline */ spinlock_t rs_lock; diff --git a/net/rds/send.c b/net/rds/send.c index b2fccfc20769..4629a0b63bbd 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -507,12 +507,13 @@ EXPORT_SYMBOL_GPL(rds_send_get_message); */ void rds_send_remove_from_sock(struct list_head *messages, int status) { - unsigned long flags = 0; /* silence gcc :P */ + unsigned long flags; struct rds_sock *rs = NULL; struct rds_message *rm; - local_irq_save(flags); while (!list_empty(messages)) { + int was_on_sock = 0; + rm = list_entry(messages->next, struct rds_message, m_conn_item); list_del_init(&rm->m_conn_item); @@ -527,20 +528,19 @@ void rds_send_remove_from_sock(struct list_head *messages, int status) * while we're messing with it. It does not prevent the * message from being removed from the socket, though. */ - spin_lock(&rm->m_rs_lock); + spin_lock_irqsave(&rm->m_rs_lock, flags); if (!test_bit(RDS_MSG_ON_SOCK, &rm->m_flags)) goto unlock_and_drop; if (rs != rm->m_rs) { if (rs) { - spin_unlock(&rs->rs_lock); rds_wake_sk_sleep(rs); sock_put(rds_rs_to_sk(rs)); } rs = rm->m_rs; - spin_lock(&rs->rs_lock); sock_hold(rds_rs_to_sk(rs)); } + spin_lock(&rs->rs_lock); if (test_and_clear_bit(RDS_MSG_ON_SOCK, &rm->m_flags)) { struct rds_rdma_op *ro = rm->m_rdma_op; @@ -557,21 +557,22 @@ void rds_send_remove_from_sock(struct list_head *messages, int status) notifier->n_status = status; rm->m_rdma_op->r_notifier = NULL; } - rds_message_put(rm); + was_on_sock = 1; rm->m_rs = NULL; } + spin_unlock(&rs->rs_lock); unlock_and_drop: - spin_unlock(&rm->m_rs_lock); + spin_unlock_irqrestore(&rm->m_rs_lock, flags); rds_message_put(rm); + if (was_on_sock) + rds_message_put(rm); } if (rs) { - spin_unlock(&rs->rs_lock); rds_wake_sk_sleep(rs); sock_put(rds_rs_to_sk(rs)); } - local_irq_restore(flags); } /* @@ -633,9 +634,6 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) list_move(&rm->m_sock_item, &list); rds_send_sndbuf_remove(rs, rm); clear_bit(RDS_MSG_ON_SOCK, &rm->m_flags); - - /* If this is a RDMA operation, notify the app. */ - __rds_rdma_send_complete(rs, rm, RDS_RDMA_CANCELED); } /* order flag updates with the rs lock */ @@ -644,9 +642,6 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) spin_unlock_irqrestore(&rs->rs_lock, flags); - if (wake) - rds_wake_sk_sleep(rs); - conn = NULL; /* now remove the messages from the conn list as needed */ @@ -654,6 +649,10 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) /* We do this here rather than in the loop above, so that * we don't have to nest m_rs_lock under rs->rs_lock */ spin_lock_irqsave(&rm->m_rs_lock, flags2); + /* If this is a RDMA operation, notify the app. */ + spin_lock(&rs->rs_lock); + __rds_rdma_send_complete(rs, rm, RDS_RDMA_CANCELED); + spin_unlock(&rs->rs_lock); rm->m_rs = NULL; spin_unlock_irqrestore(&rm->m_rs_lock, flags2); @@ -682,6 +681,9 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) if (conn) spin_unlock_irqrestore(&conn->c_lock, flags); + if (wake) + rds_wake_sk_sleep(rs); + while (!list_empty(&list)) { rm = list_entry(list.next, struct rds_message, m_sock_item); list_del_init(&rm->m_sock_item); @@ -815,7 +817,7 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, int ret = 0; int queued = 0, allocated_mr = 0; int nonblock = msg->msg_flags & MSG_DONTWAIT; - long timeo = sock_rcvtimeo(sk, nonblock); + long timeo = sock_sndtimeo(sk, nonblock); /* Mirror Linux UDP mirror of BSD error message compatibility */ /* XXX: Perhaps MSG_MORE someday */ @@ -894,8 +896,10 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, queue_delayed_work(rds_wq, &conn->c_conn_w, 0); ret = rds_cong_wait(conn->c_fcong, dport, nonblock, rs); - if (ret) + if (ret) { + rs->rs_seen_congestion = 1; goto out; + } while (!rds_send_queue_rm(rs, conn, rm, rs->rs_bound_port, dport, &queued)) { diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index c00dafffbb5a..40bfcf887465 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.c @@ -97,6 +97,7 @@ int rds_tcp_inc_copy_to_user(struct rds_incoming *inc, struct iovec *first_iov, goto out; } + rds_stats_add(s_copy_to_user, to_copy); size -= to_copy; ret += to_copy; skb_off += to_copy; diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c index 34fdcc059e54..a28b895ff0d1 100644 --- a/net/rds/tcp_send.c +++ b/net/rds/tcp_send.c @@ -240,7 +240,9 @@ void rds_tcp_write_space(struct sock *sk) tc->t_last_seen_una = rds_tcp_snd_una(tc); rds_send_drop_acked(conn, rds_tcp_snd_una(tc), rds_tcp_is_acked); - queue_delayed_work(rds_wq, &conn->c_send_w, 0); + if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) + queue_delayed_work(rds_wq, &conn->c_send_w, 0); + out: read_unlock(&sk->sk_callback_lock); diff --git a/net/rds/threads.c b/net/rds/threads.c index 00fa10e59af8..786c20eaaf5e 100644 --- a/net/rds/threads.c +++ b/net/rds/threads.c @@ -259,7 +259,7 @@ void rds_threads_exit(void) int __init rds_threads_init(void) { - rds_wq = create_singlethread_workqueue("krdsd"); + rds_wq = create_workqueue("krdsd"); if (rds_wq == NULL) return -ENOMEM; diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index a3bfd4064912..90a051912c03 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -558,10 +558,7 @@ static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1, struct tipc_media_addr *unused2) { - static int send_count = 0; - int bp_index; - int swap_time; /* Prepare buffer for broadcasting (if first time trying to send it) */ @@ -575,11 +572,6 @@ static int tipc_bcbearer_send(struct sk_buff *buf, msg_set_mc_netid(msg, tipc_net_id); } - /* Determine if bearer pairs should be swapped following this attempt */ - - if ((swap_time = (++send_count >= 10))) - send_count = 0; - /* Send buffer over bearers until all targets reached */ bcbearer->remains = tipc_cltr_bcast_nodes; @@ -595,21 +587,22 @@ static int tipc_bcbearer_send(struct sk_buff *buf, if (bcbearer->remains_new.count == bcbearer->remains.count) continue; /* bearer pair doesn't add anything */ - if (!p->publ.blocked && - !p->media->send_msg(buf, &p->publ, &p->media->bcast_addr)) { - if (swap_time && s && !s->publ.blocked) - goto swap; - else - goto update; + if (p->publ.blocked || + p->media->send_msg(buf, &p->publ, &p->media->bcast_addr)) { + /* unable to send on primary bearer */ + if (!s || s->publ.blocked || + s->media->send_msg(buf, &s->publ, + &s->media->bcast_addr)) { + /* unable to send on either bearer */ + continue; + } + } + + if (s) { + bcbearer->bpairs[bp_index].primary = s; + bcbearer->bpairs[bp_index].secondary = p; } - if (!s || s->publ.blocked || - s->media->send_msg(buf, &s->publ, &s->media->bcast_addr)) - continue; /* unable to send using bearer pair */ -swap: - bcbearer->bpairs[bp_index].primary = s; - bcbearer->bpairs[bp_index].secondary = p; -update: if (bcbearer->remains_new.count == 0) return 0; diff --git a/net/tipc/link.c b/net/tipc/link.c index 1a7e4665af80..49f2be8622a9 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1553,7 +1553,7 @@ u32 tipc_link_push_packet(struct link *l_ptr) /* Continue retransmission now, if there is anything: */ - if (r_q_size && buf && !skb_cloned(buf)) { + if (r_q_size && buf) { msg_set_ack(buf_msg(buf), mod(l_ptr->next_in_no - 1)); msg_set_bcast_ack(buf_msg(buf), l_ptr->owner->bclink.last_in); if (tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { @@ -1722,15 +1722,16 @@ void tipc_link_retransmit(struct link *l_ptr, struct sk_buff *buf, dbg("Retransmitting %u in link %x\n", retransmits, l_ptr); if (tipc_bearer_congested(l_ptr->b_ptr, l_ptr)) { - if (!skb_cloned(buf)) { + if (l_ptr->retransm_queue_size == 0) { msg_dbg(msg, ">NO_RETR->BCONG>"); dbg_print_link(l_ptr, " "); l_ptr->retransm_queue_head = msg_seqno(msg); l_ptr->retransm_queue_size = retransmits; - return; } else { - /* Don't retransmit if driver already has the buffer */ + err("Unexpected retransmit on link %s (qsize=%d)\n", + l_ptr->name, l_ptr->retransm_queue_size); } + return; } else { /* Detect repeated retransmit failures on uncongested bearer */ @@ -1745,7 +1746,7 @@ void tipc_link_retransmit(struct link *l_ptr, struct sk_buff *buf, } } - while (retransmits && (buf != l_ptr->next_out) && buf && !skb_cloned(buf)) { + while (retransmits && (buf != l_ptr->next_out) && buf) { msg = buf_msg(buf); msg_set_ack(msg, mod(l_ptr->next_in_no - 1)); msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); |