diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/Makefile | 3 | ||||
-rw-r--r-- | net/core/dev.c | 562 | ||||
-rw-r--r-- | net/core/dev_addr_lists.c | 115 | ||||
-rw-r--r-- | net/core/dev_ioctl.c | 2 | ||||
-rw-r--r-- | net/core/flow_dissector.c | 6 | ||||
-rw-r--r-- | net/core/neighbour.c | 477 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 82 | ||||
-rw-r--r-- | net/core/net-sysfs.h | 2 | ||||
-rw-r--r-- | net/core/netclassid_cgroup.c | 120 | ||||
-rw-r--r-- | net/core/netpoll.c | 4 | ||||
-rw-r--r-- | net/core/netprio_cgroup.c | 2 | ||||
-rw-r--r-- | net/core/pktgen.c | 88 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 176 | ||||
-rw-r--r-- | net/core/skbuff.c | 366 | ||||
-rw-r--r-- | net/core/sock.c | 43 | ||||
-rw-r--r-- | net/core/stream.c | 2 | ||||
-rw-r--r-- | net/core/sysctl_net_core.c | 3 |
17 files changed, 1368 insertions, 685 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index b33b996f5dd6..9628c20acff6 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -21,4 +21,5 @@ obj-$(CONFIG_FIB_RULES) += fib_rules.o obj-$(CONFIG_TRACEPOINTS) += net-traces.o obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o -obj-$(CONFIG_NETPRIO_CGROUP) += netprio_cgroup.o +obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o +obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o diff --git a/net/core/dev.c b/net/core/dev.c index 2e0c6a90f6f2..3721db716350 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -147,6 +147,8 @@ struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; struct list_head ptype_all __read_mostly; /* Taps */ static struct list_head offload_base __read_mostly; +static int netif_rx_internal(struct sk_buff *skb); + /* * The @dev_base_head list is protected by @dev_base_lock and the rtnl * semaphore. @@ -480,7 +482,7 @@ EXPORT_SYMBOL(dev_add_offload); * and must not be freed until after all the CPU's have gone * through a quiescent state. */ -void __dev_remove_offload(struct packet_offload *po) +static void __dev_remove_offload(struct packet_offload *po) { struct list_head *head = &offload_base; struct packet_offload *po1; @@ -498,7 +500,6 @@ void __dev_remove_offload(struct packet_offload *po) out: spin_unlock(&offload_lock); } -EXPORT_SYMBOL(__dev_remove_offload); /** * dev_remove_offload - remove packet offload handler @@ -1118,6 +1119,8 @@ rollback: write_seqcount_end(&devnet_rename_seq); + netdev_adjacent_rename_links(dev, oldname); + write_lock_bh(&dev_base_lock); hlist_del_rcu(&dev->name_hlist); write_unlock_bh(&dev_base_lock); @@ -1137,6 +1140,7 @@ rollback: err = ret; write_seqcount_begin(&devnet_rename_seq); memcpy(dev->name, oldname, IFNAMSIZ); + memcpy(oldname, newname, IFNAMSIZ); goto rollback; } else { pr_err("%s: name change rollback failed: %d\n", @@ -1566,14 +1570,14 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); * are as for raw_notifier_call_chain(). */ -int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev, - struct netdev_notifier_info *info) +static int call_netdevice_notifiers_info(unsigned long val, + struct net_device *dev, + struct netdev_notifier_info *info) { ASSERT_RTNL(); netdev_notifier_info_init(info, dev); return raw_notifier_call_chain(&netdev_chain, val, info); } -EXPORT_SYMBOL(call_netdevice_notifiers_info); /** * call_netdevice_notifiers - call all network notifier blocks @@ -1699,7 +1703,7 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) skb_scrub_packet(skb, true); skb->protocol = eth_type_trans(skb, dev); - return netif_rx(skb); + return netif_rx_internal(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); @@ -2079,7 +2083,7 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) } EXPORT_SYMBOL(netif_set_real_num_tx_queues); -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS /** * netif_set_real_num_rx_queues - set actual number of RX queues used * @dev: Network device @@ -2145,30 +2149,42 @@ void __netif_schedule(struct Qdisc *q) } EXPORT_SYMBOL(__netif_schedule); -void dev_kfree_skb_irq(struct sk_buff *skb) +struct dev_kfree_skb_cb { + enum skb_free_reason reason; +}; + +static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb) { - if (atomic_dec_and_test(&skb->users)) { - struct softnet_data *sd; - unsigned long flags; + return (struct dev_kfree_skb_cb *)skb->cb; +} + +void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason) +{ + unsigned long flags; - local_irq_save(flags); - sd = &__get_cpu_var(softnet_data); - skb->next = sd->completion_queue; - sd->completion_queue = skb; - raise_softirq_irqoff(NET_TX_SOFTIRQ); - local_irq_restore(flags); + if (likely(atomic_read(&skb->users) == 1)) { + smp_rmb(); + atomic_set(&skb->users, 0); + } else if (likely(!atomic_dec_and_test(&skb->users))) { + return; } + get_kfree_skb_cb(skb)->reason = reason; + local_irq_save(flags); + skb->next = __this_cpu_read(softnet_data.completion_queue); + __this_cpu_write(softnet_data.completion_queue, skb); + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); } -EXPORT_SYMBOL(dev_kfree_skb_irq); +EXPORT_SYMBOL(__dev_kfree_skb_irq); -void dev_kfree_skb_any(struct sk_buff *skb) +void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason) { if (in_irq() || irqs_disabled()) - dev_kfree_skb_irq(skb); + __dev_kfree_skb_irq(skb, reason); else dev_kfree_skb(skb); } -EXPORT_SYMBOL(dev_kfree_skb_any); +EXPORT_SYMBOL(__dev_kfree_skb_any); /** @@ -2442,13 +2458,8 @@ static void dev_gso_skb_destructor(struct sk_buff *skb) { struct dev_gso_cb *cb; - do { - struct sk_buff *nskb = skb->next; - - skb->next = nskb->next; - nskb->next = NULL; - kfree_skb(nskb); - } while (skb->next); + kfree_skb_list(skb->next); + skb->next = NULL; cb = DEV_GSO_CB(skb); if (cb->destructor) @@ -2523,21 +2534,6 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) } EXPORT_SYMBOL(netif_skb_features); -/* - * Returns true if either: - * 1. skb has frag_list and the device doesn't support FRAGLIST, or - * 2. skb is fragmented and the device does not support SG. - */ -static inline int skb_needs_linearize(struct sk_buff *skb, - netdev_features_t features) -{ - return skb_is_nonlinear(skb) && - ((skb_has_frag_list(skb) && - !(features & NETIF_F_FRAGLIST)) || - (skb_shinfo(skb)->nr_frags && - !(features & NETIF_F_SG))); -} - int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) { @@ -2605,8 +2601,8 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, dev_queue_xmit_nit(skb, dev); skb_len = skb->len; - rc = ops->ndo_start_xmit(skb, dev); - + trace_net_dev_start_xmit(skb, dev); + rc = ops->ndo_start_xmit(skb, dev); trace_net_dev_xmit(skb, rc, dev, skb_len); if (rc == NETDEV_TX_OK) txq_trans_update(txq); @@ -2624,6 +2620,7 @@ gso: dev_queue_xmit_nit(nskb, dev); skb_len = nskb->len; + trace_net_dev_start_xmit(nskb, dev); rc = ops->ndo_start_xmit(nskb, dev); trace_net_dev_xmit(nskb, rc, dev, skb_len); if (unlikely(rc != NETDEV_TX_OK)) { @@ -2744,7 +2741,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, return rc; } -#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) static void skb_update_prio(struct sk_buff *skb) { struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); @@ -2781,8 +2778,9 @@ int dev_loopback_xmit(struct sk_buff *skb) EXPORT_SYMBOL(dev_loopback_xmit); /** - * dev_queue_xmit - transmit a buffer + * __dev_queue_xmit - transmit a buffer * @skb: buffer to transmit + * @accel_priv: private data used for L2 forwarding offload * * Queue a buffer for transmission to a network device. The caller must * have set the device and priority and built the buffer before calling @@ -3014,7 +3012,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, } skb_reset_network_header(skb); - if (!skb_get_rxhash(skb)) + if (!skb_get_hash(skb)) goto done; flow_table = rcu_dereference(rxqueue->rps_flow_table); @@ -3159,7 +3157,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) rcu_read_lock(); fl = rcu_dereference(sd->flow_limit); if (fl) { - new_flow = skb_get_rxhash(skb) & (fl->num_buckets - 1); + new_flow = skb_get_hash(skb) & (fl->num_buckets - 1); old_flow = fl->history[fl->history_head]; fl->history[fl->history_head] = new_flow; @@ -3227,22 +3225,7 @@ enqueue: return NET_RX_DROP; } -/** - * netif_rx - post buffer to the network code - * @skb: buffer to post - * - * This function receives a packet from a device driver and queues it for - * the upper (protocol) levels to process. It always succeeds. The buffer - * may be dropped during processing for congestion control or by the - * protocol layers. - * - * return values: - * NET_RX_SUCCESS (no congestion) - * NET_RX_DROP (packet was dropped) - * - */ - -int netif_rx(struct sk_buff *skb) +static int netif_rx_internal(struct sk_buff *skb) { int ret; @@ -3278,14 +3261,38 @@ int netif_rx(struct sk_buff *skb) } return ret; } + +/** + * netif_rx - post buffer to the network code + * @skb: buffer to post + * + * This function receives a packet from a device driver and queues it for + * the upper (protocol) levels to process. It always succeeds. The buffer + * may be dropped during processing for congestion control or by the + * protocol layers. + * + * return values: + * NET_RX_SUCCESS (no congestion) + * NET_RX_DROP (packet was dropped) + * + */ + +int netif_rx(struct sk_buff *skb) +{ + trace_netif_rx_entry(skb); + + return netif_rx_internal(skb); +} EXPORT_SYMBOL(netif_rx); int netif_rx_ni(struct sk_buff *skb) { int err; + trace_netif_rx_ni_entry(skb); + preempt_disable(); - err = netif_rx(skb); + err = netif_rx_internal(skb); if (local_softirq_pending()) do_softirq(); preempt_enable(); @@ -3311,7 +3318,10 @@ static void net_tx_action(struct softirq_action *h) clist = clist->next; WARN_ON(atomic_read(&skb->users)); - trace_kfree_skb(skb, net_tx_action); + if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED)) + trace_consume_skb(skb); + else + trace_kfree_skb(skb, net_tx_action); __kfree_skb(skb); } } @@ -3667,22 +3677,7 @@ static int __netif_receive_skb(struct sk_buff *skb) 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) +static int netif_receive_skb_internal(struct sk_buff *skb) { net_timestamp_check(netdev_tstamp_prequeue, skb); @@ -3708,6 +3703,28 @@ int netif_receive_skb(struct sk_buff *skb) #endif return __netif_receive_skb(skb); } + +/** + * 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) +{ + trace_netif_receive_skb_entry(skb); + + return netif_receive_skb_internal(skb); +} EXPORT_SYMBOL(netif_receive_skb); /* Network device is going away, flush any packets still pending @@ -3757,7 +3774,7 @@ static int napi_gro_complete(struct sk_buff *skb) if (ptype->type != type || !ptype->callbacks.gro_complete) continue; - err = ptype->callbacks.gro_complete(skb); + err = ptype->callbacks.gro_complete(skb, 0); break; } rcu_read_unlock(); @@ -3769,7 +3786,7 @@ static int napi_gro_complete(struct sk_buff *skb) } out: - return netif_receive_skb(skb); + return netif_receive_skb_internal(skb); } /* napi->gro_list contains packets ordered by age. @@ -3805,10 +3822,18 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff *p; unsigned int maclen = skb->dev->hard_header_len; + u32 hash = skb_get_hash_raw(skb); for (p = napi->gro_list; p; p = p->next) { unsigned long diffs; + NAPI_GRO_CB(p)->flush = 0; + + if (hash != skb_get_hash_raw(p)) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= p->vlan_tci ^ skb->vlan_tci; if (maclen == ETH_HLEN) @@ -3819,7 +3844,23 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) skb_gro_mac_header(skb), maclen); NAPI_GRO_CB(p)->same_flow = !diffs; - NAPI_GRO_CB(p)->flush = 0; + } +} + +static void skb_gro_reset_offset(struct sk_buff *skb) +{ + const struct skb_shared_info *pinfo = skb_shinfo(skb); + const skb_frag_t *frag0 = &pinfo->frags[0]; + + NAPI_GRO_CB(skb)->data_offset = 0; + NAPI_GRO_CB(skb)->frag0 = NULL; + NAPI_GRO_CB(skb)->frag0_len = 0; + + if (skb_mac_header(skb) == skb_tail_pointer(skb) && + pinfo->nr_frags && + !PageHighMem(skb_frag_page(frag0))) { + NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); + NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0); } } @@ -3838,7 +3879,9 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (skb_is_gso(skb) || skb_has_frag_list(skb)) goto normal; + skb_gro_reset_offset(skb); gro_list_prepare(napi, skb); + NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */ rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { @@ -3850,6 +3893,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; + NAPI_GRO_CB(skb)->udp_mark = 0; pp = ptype->callbacks.gro_receive(&napi->gro_list, skb); break; @@ -3874,10 +3918,23 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (same_flow) goto ok; - if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS) + if (NAPI_GRO_CB(skb)->flush) goto normal; - napi->gro_count++; + if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) { + struct sk_buff *nskb = napi->gro_list; + + /* locate the end of the list to select the 'oldest' flow */ + while (nskb->next) { + pp = &nskb->next; + nskb = *pp; + } + *pp = NULL; + nskb->next = NULL; + napi_gro_complete(nskb); + } else { + napi->gro_count++; + } NAPI_GRO_CB(skb)->count = 1; NAPI_GRO_CB(skb)->age = jiffies; skb_shinfo(skb)->gso_size = skb_gro_len(skb); @@ -3915,12 +3972,39 @@ normal: goto pull; } +struct packet_offload *gro_find_receive_by_type(__be16 type) +{ + struct list_head *offload_head = &offload_base; + struct packet_offload *ptype; + + list_for_each_entry_rcu(ptype, offload_head, list) { + if (ptype->type != type || !ptype->callbacks.gro_receive) + continue; + return ptype; + } + return NULL; +} +EXPORT_SYMBOL(gro_find_receive_by_type); + +struct packet_offload *gro_find_complete_by_type(__be16 type) +{ + struct list_head *offload_head = &offload_base; + struct packet_offload *ptype; + + list_for_each_entry_rcu(ptype, offload_head, list) { + if (ptype->type != type || !ptype->callbacks.gro_complete) + continue; + return ptype; + } + return NULL; +} +EXPORT_SYMBOL(gro_find_complete_by_type); static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) { switch (ret) { case GRO_NORMAL: - if (netif_receive_skb(skb)) + if (netif_receive_skb_internal(skb)) ret = GRO_DROP; break; @@ -3943,26 +4027,9 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) return ret; } -static void skb_gro_reset_offset(struct sk_buff *skb) -{ - const struct skb_shared_info *pinfo = skb_shinfo(skb); - const skb_frag_t *frag0 = &pinfo->frags[0]; - - NAPI_GRO_CB(skb)->data_offset = 0; - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; - - if (skb_mac_header(skb) == skb_tail_pointer(skb) && - pinfo->nr_frags && - !PageHighMem(skb_frag_page(frag0))) { - NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); - NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0); - } -} - gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { - skb_gro_reset_offset(skb); + trace_napi_gro_receive_entry(skb); return napi_skb_finish(dev_gro_receive(napi, skb), skb); } @@ -3986,8 +4053,7 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi) if (!skb) { skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD); - if (skb) - napi->skb = skb; + napi->skb = skb; } return skb; } @@ -3998,12 +4064,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff * { switch (ret) { case GRO_NORMAL: - case GRO_HELD: - skb->protocol = eth_type_trans(skb, skb->dev); - - if (ret == GRO_HELD) - skb_gro_pull(skb, -ETH_HLEN); - else if (netif_receive_skb(skb)) + if (netif_receive_skb_internal(skb)) ret = GRO_DROP; break; @@ -4012,6 +4073,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff * napi_reuse_skb(napi, skb); break; + case GRO_HELD: case GRO_MERGED: break; } @@ -4022,36 +4084,15 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff * static struct sk_buff *napi_frags_skb(struct napi_struct *napi) { struct sk_buff *skb = napi->skb; - struct ethhdr *eth; - unsigned int hlen; - unsigned int off; napi->skb = NULL; - skb_reset_mac_header(skb); - skb_gro_reset_offset(skb); - - off = skb_gro_offset(skb); - hlen = off + sizeof(*eth); - eth = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, hlen)) { - eth = skb_gro_header_slow(skb, hlen, off); - if (unlikely(!eth)) { - napi_reuse_skb(napi, skb); - skb = NULL; - goto out; - } + if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) { + napi_reuse_skb(napi, skb); + return NULL; } + skb->protocol = eth_type_trans(skb, skb->dev); - skb_gro_pull(skb, sizeof(*eth)); - - /* - * This works because the only protocols we care about don't require - * special handling. We'll fix it up properly at the end. - */ - skb->protocol = eth->h_proto; - -out: return skb; } @@ -4062,12 +4103,14 @@ gro_result_t napi_gro_frags(struct napi_struct *napi) if (!skb) return GRO_DROP; + trace_napi_gro_frags_entry(skb); + return napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); } EXPORT_SYMBOL(napi_gro_frags); /* - * net_rps_action sends any pending IPI's for rps. + * net_rps_action_and_irq_enable 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) @@ -4272,17 +4315,10 @@ EXPORT_SYMBOL(netif_napi_add); void netif_napi_del(struct napi_struct *napi) { - struct sk_buff *skb, *next; - list_del_init(&napi->dev_list); napi_free_frags(napi); - for (skb = napi->gro_list; skb; skb = next) { - next = skb->next; - skb->next = NULL; - kfree_skb(skb); - } - + kfree_skb_list(napi->gro_list); napi->gro_list = NULL; napi->gro_count = 0; } @@ -4399,19 +4435,6 @@ struct netdev_adjacent { struct rcu_head rcu; }; -static struct netdev_adjacent *__netdev_find_adj_rcu(struct net_device *dev, - struct net_device *adj_dev, - struct list_head *adj_list) -{ - struct netdev_adjacent *adj; - - list_for_each_entry_rcu(adj, adj_list, list) { - if (adj->dev == adj_dev) - return adj; - } - return NULL; -} - static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev, struct net_device *adj_dev, struct list_head *adj_list) @@ -4450,13 +4473,12 @@ EXPORT_SYMBOL(netdev_has_upper_dev); * Find out if a device is linked to an upper device and return true in case * it is. The caller must hold the RTNL lock. */ -bool netdev_has_any_upper_dev(struct net_device *dev) +static bool netdev_has_any_upper_dev(struct net_device *dev) { ASSERT_RTNL(); return !list_empty(&dev->all_adj_list.upper); } -EXPORT_SYMBOL(netdev_has_any_upper_dev); /** * netdev_master_upper_dev_get - Get master upper device @@ -4576,6 +4598,27 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); /** + * netdev_lower_get_first_private_rcu - Get the first ->private from the + * lower neighbour list, RCU + * variant + * @dev: device + * + * Gets the first netdev_adjacent->private from the dev's lower neighbour + * list. The caller must hold RCU read lock. + */ +void *netdev_lower_get_first_private_rcu(struct net_device *dev) +{ + struct netdev_adjacent *lower; + + lower = list_first_or_null_rcu(&dev->adj_list.lower, + struct netdev_adjacent, list); + if (lower) + return lower->private; + return NULL; +} +EXPORT_SYMBOL(netdev_lower_get_first_private_rcu); + +/** * netdev_master_upper_dev_get_rcu - Get master upper device * @dev: device * @@ -4594,13 +4637,36 @@ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) } EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); +int netdev_adjacent_sysfs_add(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list) +{ + char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? + "upper_%s" : "lower_%s", adj_dev->name); + return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), + linkname); +} +void netdev_adjacent_sysfs_del(struct net_device *dev, + char *name, + struct list_head *dev_list) +{ + char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? + "upper_%s" : "lower_%s", name); + sysfs_remove_link(&(dev->dev.kobj), linkname); +} + +#define netdev_adjacent_is_neigh_list(dev, dev_list) \ + (dev_list == &dev->adj_list.upper || \ + dev_list == &dev->adj_list.lower) + static int __netdev_adjacent_dev_insert(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list, void *private, bool master) { struct netdev_adjacent *adj; - char linkname[IFNAMSIZ+7]; int ret; adj = __netdev_find_adj(dev, adj_dev, dev_list); @@ -4623,16 +4689,8 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, pr_debug("dev_hold for %s, because of link added from %s to %s\n", adj_dev->name, dev->name, adj_dev->name); - if (dev_list == &dev->adj_list.lower) { - sprintf(linkname, "lower_%s", adj_dev->name); - ret = sysfs_create_link(&(dev->dev.kobj), - &(adj_dev->dev.kobj), linkname); - if (ret) - goto free_adj; - } else if (dev_list == &dev->adj_list.upper) { - sprintf(linkname, "upper_%s", adj_dev->name); - ret = sysfs_create_link(&(dev->dev.kobj), - &(adj_dev->dev.kobj), linkname); + if (netdev_adjacent_is_neigh_list(dev, dev_list)) { + ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list); if (ret) goto free_adj; } @@ -4652,14 +4710,8 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, return 0; remove_symlinks: - if (dev_list == &dev->adj_list.lower) { - sprintf(linkname, "lower_%s", adj_dev->name); - sysfs_remove_link(&(dev->dev.kobj), linkname); - } else if (dev_list == &dev->adj_list.upper) { - sprintf(linkname, "upper_%s", adj_dev->name); - sysfs_remove_link(&(dev->dev.kobj), linkname); - } - + if (netdev_adjacent_is_neigh_list(dev, dev_list)) + netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); free_adj: kfree(adj); dev_put(adj_dev); @@ -4667,12 +4719,11 @@ free_adj: return ret; } -void __netdev_adjacent_dev_remove(struct net_device *dev, - struct net_device *adj_dev, - struct list_head *dev_list) +static void __netdev_adjacent_dev_remove(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list) { struct netdev_adjacent *adj; - char linkname[IFNAMSIZ+7]; adj = __netdev_find_adj(dev, adj_dev, dev_list); @@ -4692,13 +4743,8 @@ void __netdev_adjacent_dev_remove(struct net_device *dev, if (adj->master) sysfs_remove_link(&(dev->dev.kobj), "master"); - if (dev_list == &dev->adj_list.lower) { - sprintf(linkname, "lower_%s", adj_dev->name); - sysfs_remove_link(&(dev->dev.kobj), linkname); - } else if (dev_list == &dev->adj_list.upper) { - sprintf(linkname, "upper_%s", adj_dev->name); - sysfs_remove_link(&(dev->dev.kobj), linkname); - } + if (netdev_adjacent_is_neigh_list(dev, dev_list)) + netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); list_del_rcu(&adj->list); pr_debug("dev_put for %s, because link removed from %s to %s\n", @@ -4707,11 +4753,11 @@ void __netdev_adjacent_dev_remove(struct net_device *dev, kfree_rcu(adj, rcu); } -int __netdev_adjacent_dev_link_lists(struct net_device *dev, - struct net_device *upper_dev, - struct list_head *up_list, - struct list_head *down_list, - void *private, bool master) +static int __netdev_adjacent_dev_link_lists(struct net_device *dev, + struct net_device *upper_dev, + struct list_head *up_list, + struct list_head *down_list, + void *private, bool master) { int ret; @@ -4730,8 +4776,8 @@ int __netdev_adjacent_dev_link_lists(struct net_device *dev, return 0; } -int __netdev_adjacent_dev_link(struct net_device *dev, - struct net_device *upper_dev) +static int __netdev_adjacent_dev_link(struct net_device *dev, + struct net_device *upper_dev) { return __netdev_adjacent_dev_link_lists(dev, upper_dev, &dev->all_adj_list.upper, @@ -4739,26 +4785,26 @@ int __netdev_adjacent_dev_link(struct net_device *dev, NULL, false); } -void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, - struct net_device *upper_dev, - struct list_head *up_list, - struct list_head *down_list) +static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, + struct net_device *upper_dev, + struct list_head *up_list, + struct list_head *down_list) { __netdev_adjacent_dev_remove(dev, upper_dev, up_list); __netdev_adjacent_dev_remove(upper_dev, dev, down_list); } -void __netdev_adjacent_dev_unlink(struct net_device *dev, - struct net_device *upper_dev) +static void __netdev_adjacent_dev_unlink(struct net_device *dev, + struct net_device *upper_dev) { __netdev_adjacent_dev_unlink_lists(dev, upper_dev, &dev->all_adj_list.upper, &upper_dev->all_adj_list.lower); } -int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, - struct net_device *upper_dev, - void *private, bool master) +static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, + struct net_device *upper_dev, + void *private, bool master) { int ret = __netdev_adjacent_dev_link(dev, upper_dev); @@ -4777,8 +4823,8 @@ int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, return 0; } -void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, - struct net_device *upper_dev) +static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, + struct net_device *upper_dev) { __netdev_adjacent_dev_unlink(dev, upper_dev); __netdev_adjacent_dev_unlink_lists(dev, upper_dev, @@ -4967,20 +5013,24 @@ void netdev_upper_dev_unlink(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_dev_unlink); -void *netdev_lower_dev_get_private_rcu(struct net_device *dev, - struct net_device *lower_dev) +void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) { - struct netdev_adjacent *lower; + struct netdev_adjacent *iter; - if (!lower_dev) - return NULL; - lower = __netdev_find_adj_rcu(dev, lower_dev, &dev->adj_list.lower); - if (!lower) - return NULL; + list_for_each_entry(iter, &dev->adj_list.upper, list) { + netdev_adjacent_sysfs_del(iter->dev, oldname, + &iter->dev->adj_list.lower); + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.lower); + } - return lower->private; + list_for_each_entry(iter, &dev->adj_list.lower, list) { + netdev_adjacent_sysfs_del(iter->dev, oldname, + &iter->dev->adj_list.upper); + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.upper); + } } -EXPORT_SYMBOL(netdev_lower_dev_get_private_rcu); void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev) @@ -5314,6 +5364,17 @@ int dev_change_flags(struct net_device *dev, unsigned int flags) } EXPORT_SYMBOL(dev_change_flags); +static int __dev_set_mtu(struct net_device *dev, int new_mtu) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_change_mtu) + return ops->ndo_change_mtu(dev, new_mtu); + + dev->mtu = new_mtu; + return 0; +} + /** * dev_set_mtu - Change maximum transfer unit * @dev: device @@ -5323,8 +5384,7 @@ EXPORT_SYMBOL(dev_change_flags); */ int dev_set_mtu(struct net_device *dev, int new_mtu) { - const struct net_device_ops *ops = dev->netdev_ops; - int err; + int err, orig_mtu; if (new_mtu == dev->mtu) return 0; @@ -5336,14 +5396,25 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) if (!netif_device_present(dev)) return -ENODEV; - err = 0; - if (ops->ndo_change_mtu) - err = ops->ndo_change_mtu(dev, new_mtu); - else - dev->mtu = new_mtu; + err = call_netdevice_notifiers(NETDEV_PRECHANGEMTU, dev); + err = notifier_to_errno(err); + if (err) + return err; - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + orig_mtu = dev->mtu; + err = __dev_set_mtu(dev, new_mtu); + + if (!err) { + err = call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + err = notifier_to_errno(err); + if (err) { + /* setting mtu back and notifying everyone again, + * so that they have a chance to revert changes. + */ + __dev_set_mtu(dev, orig_mtu); + call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + } + } return err; } EXPORT_SYMBOL(dev_set_mtu); @@ -5697,7 +5768,7 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev, } EXPORT_SYMBOL(netif_stacked_transfer_operstate); -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS static int netif_alloc_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; @@ -5836,13 +5907,8 @@ int register_netdevice(struct net_device *dev) dev->features |= NETIF_F_SOFT_FEATURES; dev->wanted_features = dev->features & dev->hw_features; - /* Turn on no cache copy if HW is doing checksum */ if (!(dev->flags & IFF_LOOPBACK)) { dev->hw_features |= NETIF_F_NOCACHE_COPY; - if (dev->features & NETIF_F_ALL_CSUM) { - dev->wanted_features |= NETIF_F_NOCACHE_COPY; - dev->features |= NETIF_F_NOCACHE_COPY; - } } /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. @@ -6247,7 +6313,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, return NULL; } -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS if (rxqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n"); return NULL; @@ -6303,7 +6369,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, if (netif_alloc_netdev_queues(dev)) goto free_all; -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS dev->num_rx_queues = rxqs; dev->real_num_rx_queues = rxqs; if (netif_alloc_rx_queues(dev)) @@ -6323,7 +6389,7 @@ free_all: free_pcpu: free_percpu(dev->pcpu_refcnt); netif_free_tx_queues(dev); -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS kfree(dev->_rx); #endif @@ -6348,7 +6414,7 @@ void free_netdev(struct net_device *dev) release_net(dev_net(dev)); netif_free_tx_queues(dev); -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS kfree(dev->_rx); #endif @@ -6618,11 +6684,11 @@ static int dev_cpu_callback(struct notifier_block *nfb, /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { - netif_rx(skb); + netif_rx_internal(skb); input_queue_head_incr(oldsd); } while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { - netif_rx(skb); + netif_rx_internal(skb); input_queue_head_incr(oldsd); } @@ -6935,28 +7001,18 @@ 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; - sd->csd.flags = 0; sd->cpu = i; #endif sd->backlog.poll = process_backlog; sd->backlog.weight = weight_p; - sd->backlog.gro_list = NULL; - sd->backlog.gro_count = 0; - -#ifdef CONFIG_NET_FLOW_LIMIT - sd->flow_limit = NULL; -#endif } dev_boot_phase = 0; diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index ec40a849fc42..329d5794e7dc 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -38,7 +38,7 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, ha->type = addr_type; ha->refcount = 1; ha->global_use = global; - ha->synced = sync; + ha->synced = sync ? 1 : 0; ha->sync_cnt = 0; list_add_tail_rcu(&ha->list, &list->list); list->count++; @@ -48,7 +48,8 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, - unsigned char addr_type, bool global, bool sync) + unsigned char addr_type, bool global, bool sync, + int sync_count) { struct netdev_hw_addr *ha; @@ -66,10 +67,10 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, ha->global_use = true; } if (sync) { - if (ha->synced) + if (ha->synced && sync_count) return -EEXIST; else - ha->synced = true; + ha->synced++; } ha->refcount++; return 0; @@ -84,7 +85,8 @@ static int __hw_addr_add(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type) { - return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false); + return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false, + 0); } static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, @@ -101,7 +103,7 @@ static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, ha->global_use = false; if (sync) - ha->synced = false; + ha->synced--; if (--ha->refcount) return 0; @@ -139,7 +141,7 @@ static int __hw_addr_sync_one(struct netdev_hw_addr_list *to_list, int err; err = __hw_addr_add_ex(to_list, ha->addr, addr_len, ha->type, - false, true); + false, true, ha->sync_cnt); if (err && err != -EEXIST) return err; @@ -186,47 +188,6 @@ static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, return err; } -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, type); - } -} -EXPORT_SYMBOL(__hw_addr_del_multiple); - /* This function only works where there is a strict 1-1 relationship * between source and destionation of they synch. If you ever need to * sync addresses to more then 1 destination, you need to use @@ -264,7 +225,7 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, } EXPORT_SYMBOL(__hw_addr_unsync); -void __hw_addr_flush(struct netdev_hw_addr_list *list) +static void __hw_addr_flush(struct netdev_hw_addr_list *list) { struct netdev_hw_addr *ha, *tmp; @@ -274,7 +235,6 @@ void __hw_addr_flush(struct netdev_hw_addr_list *list) } list->count = 0; } -EXPORT_SYMBOL(__hw_addr_flush); void __hw_addr_init(struct netdev_hw_addr_list *list) { @@ -400,59 +360,6 @@ int dev_addr_del(struct net_device *dev, const unsigned char *addr, } 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 supplying the addresses to be deleted - * @addr_type: address type - 0 means type will be 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 */ @@ -676,7 +583,7 @@ static int __dev_mc_add(struct net_device *dev, const unsigned char *addr, netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_MULTICAST, global, false); + NETDEV_HW_ADDR_T_MULTICAST, global, false, 0); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 5b7d0e1d0664..cf999e09bcd2 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -327,6 +327,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) cmd == SIOCBRADDIF || cmd == SIOCBRDELIF || cmd == SIOCSHWTSTAMP || + cmd == SIOCGHWTSTAMP || cmd == SIOCWANDEV) { err = -EOPNOTSUPP; if (ops->ndo_do_ioctl) { @@ -546,6 +547,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) */ default: if (cmd == SIOCWANDEV || + cmd == SIOCGHWTSTAMP || (cmd >= SIOCDEVPRIVATE && cmd <= SIOCDEVPRIVATE + 15)) { dev_load(net, ifr.ifr_name); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 2fc5beaf5783..87577d447554 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -202,12 +202,12 @@ static __always_inline u32 __flow_hash_1word(u32 a) } /* - * __skb_get_rxhash: calculate a flow hash based on src/dst addresses + * __skb_get_hash: calculate a flow hash based on src/dst addresses * and src/dst port numbers. Sets rxhash in skb to non-zero hash value * on success, zero indicates no valid hash. Also, sets l4_rxhash in skb * if hash is a canonical 4-tuple hash over transport ports. */ -void __skb_get_rxhash(struct sk_buff *skb) +void __skb_get_hash(struct sk_buff *skb) { struct flow_keys keys; u32 hash; @@ -234,7 +234,7 @@ void __skb_get_rxhash(struct sk_buff *skb) skb->rxhash = hash; } -EXPORT_SYMBOL(__skb_get_rxhash); +EXPORT_SYMBOL(__skb_get_hash); /* * Returns a Tx hash based on the given packet descriptor a Tx queues' number diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 932c6d7cf666..b9e9e0d38672 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -38,6 +38,8 @@ #include <linux/random.h> #include <linux/string.h> #include <linux/log2.h> +#include <linux/inetdevice.h> +#include <net/addrconf.h> #define DEBUG #define NEIGH_DEBUG 1 @@ -115,7 +117,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh) unsigned long neigh_rand_reach_time(unsigned long base) { - return base ? (net_random() % base) + (base >> 1) : 0; + return base ? (prandom_u32() % base) + (base >> 1) : 0; } EXPORT_SYMBOL(neigh_rand_reach_time); @@ -497,7 +499,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, goto out_neigh_release; } - n->confirmed = jiffies - (n->parms->base_reachable_time << 1); + n->confirmed = jiffies - (NEIGH_VAR(n->parms, BASE_REACHABLE_TIME) << 1); write_lock_bh(&tbl->lock); nht = rcu_dereference_protected(tbl->nht, @@ -776,7 +778,7 @@ static void neigh_periodic_work(struct work_struct *work) tbl->last_rand = jiffies; for (p = &tbl->parms; p; p = p->next) p->reachable_time = - neigh_rand_reach_time(p->base_reachable_time); + neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); } for (i = 0 ; i < (1 << nht->hash_shift); i++) { @@ -799,7 +801,7 @@ static void neigh_periodic_work(struct work_struct *work) if (atomic_read(&n->refcnt) == 1 && (state == NUD_FAILED || - time_after(jiffies, n->used + n->parms->gc_staletime))) { + time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { *np = n->next; n->dead = 1; write_unlock(&n->lock); @@ -822,12 +824,12 @@ next_elt: lockdep_is_held(&tbl->lock)); } out: - /* Cycle through all hash buckets every base_reachable_time/2 ticks. - * ARP entry timeouts range from 1/2 base_reachable_time to 3/2 - * base_reachable_time. + /* Cycle through all hash buckets every BASE_REACHABLE_TIME/2 ticks. + * ARP entry timeouts range from 1/2 BASE_REACHABLE_TIME to 3/2 + * BASE_REACHABLE_TIME. */ - schedule_delayed_work(&tbl->gc_work, - tbl->parms.base_reachable_time >> 1); + queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, + NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME) >> 1); write_unlock_bh(&tbl->lock); } @@ -835,8 +837,9 @@ static __inline__ int neigh_max_probes(struct neighbour *n) { struct neigh_parms *p = n->parms; return (n->nud_state & NUD_PROBE) ? - p->ucast_probes : - p->ucast_probes + p->app_probes + p->mcast_probes; + NEIGH_VAR(p, UCAST_PROBES) : + NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) + + NEIGH_VAR(p, MCAST_PROBES); } static void neigh_invalidate(struct neighbour *neigh) @@ -901,12 +904,13 @@ static void neigh_timer_handler(unsigned long arg) neigh_dbg(2, "neigh %p is still alive\n", neigh); next = neigh->confirmed + neigh->parms->reachable_time; } else if (time_before_eq(now, - neigh->used + neigh->parms->delay_probe_time)) { + neigh->used + + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { neigh_dbg(2, "neigh %p is delayed\n", neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; neigh_suspect(neigh); - next = now + neigh->parms->delay_probe_time; + next = now + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME); } else { neigh_dbg(2, "neigh %p is suspected\n", neigh); neigh->nud_state = NUD_STALE; @@ -916,7 +920,8 @@ static void neigh_timer_handler(unsigned long arg) } } else if (state & NUD_DELAY) { if (time_before_eq(now, - neigh->confirmed + neigh->parms->delay_probe_time)) { + neigh->confirmed + + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) { neigh_dbg(2, "neigh %p is now reachable\n", neigh); neigh->nud_state = NUD_REACHABLE; neigh->updated = jiffies; @@ -928,11 +933,11 @@ static void neigh_timer_handler(unsigned long arg) neigh->nud_state = NUD_PROBE; neigh->updated = jiffies; atomic_set(&neigh->probes, 0); - next = now + neigh->parms->retrans_time; + next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME); } } else { /* NUD_PROBE|NUD_INCOMPLETE */ - next = now + neigh->parms->retrans_time; + next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME); } if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) && @@ -973,13 +978,16 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) goto out_unlock_bh; if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) { - if (neigh->parms->mcast_probes + neigh->parms->app_probes) { + if (NEIGH_VAR(neigh->parms, MCAST_PROBES) + + NEIGH_VAR(neigh->parms, APP_PROBES)) { unsigned long next, now = jiffies; - atomic_set(&neigh->probes, neigh->parms->ucast_probes); + atomic_set(&neigh->probes, + NEIGH_VAR(neigh->parms, UCAST_PROBES)); neigh->nud_state = NUD_INCOMPLETE; neigh->updated = now; - next = now + max(neigh->parms->retrans_time, HZ/2); + next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), + HZ/2); neigh_add_timer(neigh, next); immediate_probe = true; } else { @@ -994,14 +1002,14 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) neigh_dbg(2, "neigh %p is delayed\n", neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; - neigh_add_timer(neigh, - jiffies + neigh->parms->delay_probe_time); + neigh_add_timer(neigh, jiffies + + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME)); } if (neigh->nud_state == NUD_INCOMPLETE) { if (skb) { while (neigh->arp_queue_len_bytes + skb->truesize > - neigh->parms->queue_len_bytes) { + NEIGH_VAR(neigh->parms, QUEUE_LEN_BYTES)) { struct sk_buff *buff; buff = __skb_dequeue(&neigh->arp_queue); @@ -1171,7 +1179,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh_update_hhs(neigh); if (!(new & NUD_CONNECTED)) neigh->confirmed = jiffies - - (neigh->parms->base_reachable_time << 1); + (NEIGH_VAR(neigh->parms, BASE_REACHABLE_TIME) << 1); notify = 1; } if (new == old) @@ -1231,6 +1239,21 @@ out: } EXPORT_SYMBOL(neigh_update); +/* Update the neigh to listen temporarily for probe responses, even if it is + * in a NUD_FAILED state. The caller has to hold neigh->lock for writing. + */ +void __neigh_set_probe_once(struct neighbour *neigh) +{ + neigh->updated = jiffies; + if (!(neigh->nud_state & NUD_FAILED)) + return; + neigh->nud_state = NUD_PROBE; + atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES)); + neigh_add_timer(neigh, + jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME)); +} +EXPORT_SYMBOL(__neigh_set_probe_once); + struct neighbour *neigh_event_ns(struct neigh_table *tbl, u8 *lladdr, void *saddr, struct net_device *dev) @@ -1392,9 +1415,11 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb) { unsigned long now = jiffies; - unsigned long sched_next = now + (net_random() % p->proxy_delay); - if (tbl->proxy_queue.qlen > p->proxy_qlen) { + unsigned long sched_next = now + (prandom_u32() % + NEIGH_VAR(p, PROXY_DELAY)); + + if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) { kfree_skb(skb); return; } @@ -1441,7 +1466,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, p->tbl = tbl; atomic_set(&p->refcnt, 1); p->reachable_time = - neigh_rand_reach_time(p->base_reachable_time); + neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); dev_hold(dev); p->dev = dev; write_pnet(&p->net, hold_net(net)); @@ -1458,6 +1483,8 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, p->next = tbl->parms.next; tbl->parms.next = p; write_unlock_bh(&tbl->lock); + + neigh_parms_data_state_cleanall(p); } return p; } @@ -1510,7 +1537,7 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl) write_pnet(&tbl->parms.net, &init_net); atomic_set(&tbl->parms.refcnt, 1); tbl->parms.reachable_time = - neigh_rand_reach_time(tbl->parms.base_reachable_time); + neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME)); tbl->stats = alloc_percpu(struct neigh_statistics); if (!tbl->stats) @@ -1538,7 +1565,8 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl) rwlock_init(&tbl->lock); INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); - schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time); + queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, + tbl->parms.reachable_time); setup_timer(&tbl->proxy_timer, neigh_proxy_process, (unsigned long)tbl); skb_queue_head_init_class(&tbl->proxy_queue, &neigh_table_proxy_queue_class); @@ -1778,24 +1806,32 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) if ((parms->dev && nla_put_u32(skb, NDTPA_IFINDEX, parms->dev->ifindex)) || nla_put_u32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)) || - nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, parms->queue_len_bytes) || + nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, + NEIGH_VAR(parms, QUEUE_LEN_BYTES)) || /* approximative value for deprecated QUEUE_LEN (in packets) */ nla_put_u32(skb, NDTPA_QUEUE_LEN, - parms->queue_len_bytes / SKB_TRUESIZE(ETH_FRAME_LEN)) || - nla_put_u32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen) || - nla_put_u32(skb, NDTPA_APP_PROBES, parms->app_probes) || - nla_put_u32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes) || - nla_put_u32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes) || + NEIGH_VAR(parms, QUEUE_LEN_BYTES) / SKB_TRUESIZE(ETH_FRAME_LEN)) || + nla_put_u32(skb, NDTPA_PROXY_QLEN, NEIGH_VAR(parms, PROXY_QLEN)) || + nla_put_u32(skb, NDTPA_APP_PROBES, NEIGH_VAR(parms, APP_PROBES)) || + nla_put_u32(skb, NDTPA_UCAST_PROBES, + NEIGH_VAR(parms, UCAST_PROBES)) || + nla_put_u32(skb, NDTPA_MCAST_PROBES, + NEIGH_VAR(parms, MCAST_PROBES)) || nla_put_msecs(skb, NDTPA_REACHABLE_TIME, parms->reachable_time) || nla_put_msecs(skb, NDTPA_BASE_REACHABLE_TIME, - parms->base_reachable_time) || - nla_put_msecs(skb, NDTPA_GC_STALETIME, parms->gc_staletime) || + NEIGH_VAR(parms, BASE_REACHABLE_TIME)) || + nla_put_msecs(skb, NDTPA_GC_STALETIME, + NEIGH_VAR(parms, GC_STALETIME)) || nla_put_msecs(skb, NDTPA_DELAY_PROBE_TIME, - parms->delay_probe_time) || - nla_put_msecs(skb, NDTPA_RETRANS_TIME, parms->retrans_time) || - nla_put_msecs(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay) || - nla_put_msecs(skb, NDTPA_PROXY_DELAY, parms->proxy_delay) || - nla_put_msecs(skb, NDTPA_LOCKTIME, parms->locktime)) + NEIGH_VAR(parms, DELAY_PROBE_TIME)) || + nla_put_msecs(skb, NDTPA_RETRANS_TIME, + NEIGH_VAR(parms, RETRANS_TIME)) || + nla_put_msecs(skb, NDTPA_ANYCAST_DELAY, + NEIGH_VAR(parms, ANYCAST_DELAY)) || + nla_put_msecs(skb, NDTPA_PROXY_DELAY, + NEIGH_VAR(parms, PROXY_DELAY)) || + nla_put_msecs(skb, NDTPA_LOCKTIME, + NEIGH_VAR(parms, LOCKTIME))) goto nla_put_failure; return nla_nest_end(skb, nest); @@ -2011,44 +2047,57 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh) switch (i) { case NDTPA_QUEUE_LEN: - p->queue_len_bytes = nla_get_u32(tbp[i]) * - SKB_TRUESIZE(ETH_FRAME_LEN); + NEIGH_VAR_SET(p, QUEUE_LEN_BYTES, + nla_get_u32(tbp[i]) * + SKB_TRUESIZE(ETH_FRAME_LEN)); break; case NDTPA_QUEUE_LENBYTES: - p->queue_len_bytes = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, QUEUE_LEN_BYTES, + nla_get_u32(tbp[i])); break; case NDTPA_PROXY_QLEN: - p->proxy_qlen = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, PROXY_QLEN, + nla_get_u32(tbp[i])); break; case NDTPA_APP_PROBES: - p->app_probes = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, APP_PROBES, + nla_get_u32(tbp[i])); break; case NDTPA_UCAST_PROBES: - p->ucast_probes = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, UCAST_PROBES, + nla_get_u32(tbp[i])); break; case NDTPA_MCAST_PROBES: - p->mcast_probes = nla_get_u32(tbp[i]); + NEIGH_VAR_SET(p, MCAST_PROBES, + nla_get_u32(tbp[i])); break; case NDTPA_BASE_REACHABLE_TIME: - p->base_reachable_time = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, BASE_REACHABLE_TIME, + nla_get_msecs(tbp[i])); break; case NDTPA_GC_STALETIME: - p->gc_staletime = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, GC_STALETIME, + nla_get_msecs(tbp[i])); break; case NDTPA_DELAY_PROBE_TIME: - p->delay_probe_time = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, DELAY_PROBE_TIME, + nla_get_msecs(tbp[i])); break; case NDTPA_RETRANS_TIME: - p->retrans_time = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, RETRANS_TIME, + nla_get_msecs(tbp[i])); break; case NDTPA_ANYCAST_DELAY: - p->anycast_delay = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, ANYCAST_DELAY, + nla_get_msecs(tbp[i])); break; case NDTPA_PROXY_DELAY: - p->proxy_delay = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, PROXY_DELAY, + nla_get_msecs(tbp[i])); break; case NDTPA_LOCKTIME: - p->locktime = nla_get_msecs(tbp[i]); + NEIGH_VAR_SET(p, LOCKTIME, + nla_get_msecs(tbp[i])); break; } } @@ -2789,133 +2838,167 @@ static int proc_unres_qlen(struct ctl_table *ctl, int write, return ret; } -enum { - NEIGH_VAR_MCAST_PROBE, - NEIGH_VAR_UCAST_PROBE, - NEIGH_VAR_APP_PROBE, - NEIGH_VAR_RETRANS_TIME, - NEIGH_VAR_BASE_REACHABLE_TIME, - NEIGH_VAR_DELAY_PROBE_TIME, - NEIGH_VAR_GC_STALETIME, - NEIGH_VAR_QUEUE_LEN, - NEIGH_VAR_QUEUE_LEN_BYTES, - NEIGH_VAR_PROXY_QLEN, - NEIGH_VAR_ANYCAST_DELAY, - NEIGH_VAR_PROXY_DELAY, - NEIGH_VAR_LOCKTIME, - NEIGH_VAR_RETRANS_TIME_MS, - NEIGH_VAR_BASE_REACHABLE_TIME_MS, - NEIGH_VAR_GC_INTERVAL, - NEIGH_VAR_GC_THRESH1, - NEIGH_VAR_GC_THRESH2, - NEIGH_VAR_GC_THRESH3, - NEIGH_VAR_MAX -}; +static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev, + int family) +{ + switch (family) { + case AF_INET: + return __in_dev_arp_parms_get_rcu(dev); + case AF_INET6: + return __in6_dev_nd_parms_get_rcu(dev); + } + return NULL; +} + +static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p, + int index) +{ + struct net_device *dev; + int family = neigh_parms_family(p); + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + struct neigh_parms *dst_p = + neigh_get_dev_parms_rcu(dev, family); + + if (dst_p && !test_bit(index, dst_p->data_state)) + dst_p->data[index] = p->data[index]; + } + rcu_read_unlock(); +} + +static void neigh_proc_update(struct ctl_table *ctl, int write) +{ + struct net_device *dev = ctl->extra1; + struct neigh_parms *p = ctl->extra2; + struct net *net = neigh_parms_net(p); + int index = (int *) ctl->data - p->data; + + if (!write) + return; + + set_bit(index, p->data_state); + if (!dev) /* NULL dev means this is default value */ + neigh_copy_dflt_parms(net, p, index); +} + +static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + struct ctl_table tmp = *ctl; + int ret; + + tmp.extra1 = &zero; + tmp.extra2 = &int_max; + + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + neigh_proc_update(ctl, write); + return ret; +} + +int neigh_proc_dointvec(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} +EXPORT_SYMBOL(neigh_proc_dointvec); + +int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} +EXPORT_SYMBOL(neigh_proc_dointvec_jiffies); + +static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_userhz_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} + +int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} +EXPORT_SYMBOL(neigh_proc_dointvec_ms_jiffies); + +static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_unres_qlen(ctl, write, buffer, lenp, ppos); + + neigh_proc_update(ctl, write); + return ret; +} + +#define NEIGH_PARMS_DATA_OFFSET(index) \ + (&((struct neigh_parms *) 0)->data[index]) + +#define NEIGH_SYSCTL_ENTRY(attr, data_attr, name, mval, proc) \ + [NEIGH_VAR_ ## attr] = { \ + .procname = name, \ + .data = NEIGH_PARMS_DATA_OFFSET(NEIGH_VAR_ ## data_attr), \ + .maxlen = sizeof(int), \ + .mode = mval, \ + .proc_handler = proc, \ + } + +#define NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_zero_intmax) + +#define NEIGH_SYSCTL_JIFFIES_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_jiffies) + +#define NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_userhz_jiffies) + +#define NEIGH_SYSCTL_MS_JIFFIES_ENTRY(attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_ms_jiffies) + +#define NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(attr, data_attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_ms_jiffies) + +#define NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(attr, data_attr, name) \ + NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_unres_qlen) static struct neigh_sysctl_table { struct ctl_table_header *sysctl_header; struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1]; } neigh_sysctl_template __read_mostly = { .neigh_vars = { - [NEIGH_VAR_MCAST_PROBE] = { - .procname = "mcast_solicit", - .maxlen = sizeof(int), - .mode = 0644, - .extra1 = &zero, - .extra2 = &int_max, - .proc_handler = proc_dointvec_minmax, - }, - [NEIGH_VAR_UCAST_PROBE] = { - .procname = "ucast_solicit", - .maxlen = sizeof(int), - .mode = 0644, - .extra1 = &zero, - .extra2 = &int_max, - .proc_handler = proc_dointvec_minmax, - }, - [NEIGH_VAR_APP_PROBE] = { - .procname = "app_solicit", - .maxlen = sizeof(int), - .mode = 0644, - .extra1 = &zero, - .extra2 = &int_max, - .proc_handler = proc_dointvec_minmax, - }, - [NEIGH_VAR_RETRANS_TIME] = { - .procname = "retrans_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - [NEIGH_VAR_BASE_REACHABLE_TIME] = { - .procname = "base_reachable_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - [NEIGH_VAR_DELAY_PROBE_TIME] = { - .procname = "delay_first_probe_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - [NEIGH_VAR_GC_STALETIME] = { - .procname = "gc_stale_time", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - [NEIGH_VAR_QUEUE_LEN] = { - .procname = "unres_qlen", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_unres_qlen, - }, - [NEIGH_VAR_QUEUE_LEN_BYTES] = { - .procname = "unres_qlen_bytes", - .maxlen = sizeof(int), - .mode = 0644, - .extra1 = &zero, - .proc_handler = proc_dointvec_minmax, - }, - [NEIGH_VAR_PROXY_QLEN] = { - .procname = "proxy_qlen", - .maxlen = sizeof(int), - .mode = 0644, - .extra1 = &zero, - .extra2 = &int_max, - .proc_handler = proc_dointvec_minmax, - }, - [NEIGH_VAR_ANYCAST_DELAY] = { - .procname = "anycast_delay", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - [NEIGH_VAR_PROXY_DELAY] = { - .procname = "proxy_delay", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - [NEIGH_VAR_LOCKTIME] = { - .procname = "locktime", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_userhz_jiffies, - }, - [NEIGH_VAR_RETRANS_TIME_MS] = { - .procname = "retrans_time_ms", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_ms_jiffies, - }, - [NEIGH_VAR_BASE_REACHABLE_TIME_MS] = { - .procname = "base_reachable_time_ms", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_ms_jiffies, - }, + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_PROBES, "mcast_solicit"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(UCAST_PROBES, "ucast_solicit"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(APP_PROBES, "app_solicit"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(RETRANS_TIME, "retrans_time"), + NEIGH_SYSCTL_JIFFIES_ENTRY(BASE_REACHABLE_TIME, "base_reachable_time"), + NEIGH_SYSCTL_JIFFIES_ENTRY(DELAY_PROBE_TIME, "delay_first_probe_time"), + NEIGH_SYSCTL_JIFFIES_ENTRY(GC_STALETIME, "gc_stale_time"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(QUEUE_LEN_BYTES, "unres_qlen_bytes"), + NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(PROXY_QLEN, "proxy_qlen"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(ANYCAST_DELAY, "anycast_delay"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(PROXY_DELAY, "proxy_delay"), + NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(LOCKTIME, "locktime"), + NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(QUEUE_LEN, QUEUE_LEN_BYTES, "unres_qlen"), + NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(RETRANS_TIME_MS, RETRANS_TIME, "retrans_time_ms"), + NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(BASE_REACHABLE_TIME_MS, BASE_REACHABLE_TIME, "base_reachable_time_ms"), [NEIGH_VAR_GC_INTERVAL] = { .procname = "gc_interval", .maxlen = sizeof(int), @@ -2951,31 +3034,23 @@ static struct neigh_sysctl_table { }; int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, - char *p_name, proc_handler *handler) + proc_handler *handler) { + int i; struct neigh_sysctl_table *t; - const char *dev_name_source = NULL; + const char *dev_name_source; char neigh_path[ sizeof("net//neigh/") + IFNAMSIZ + IFNAMSIZ ]; + char *p_name; t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL); if (!t) goto err; - t->neigh_vars[NEIGH_VAR_MCAST_PROBE].data = &p->mcast_probes; - t->neigh_vars[NEIGH_VAR_UCAST_PROBE].data = &p->ucast_probes; - t->neigh_vars[NEIGH_VAR_APP_PROBE].data = &p->app_probes; - t->neigh_vars[NEIGH_VAR_RETRANS_TIME].data = &p->retrans_time; - t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].data = &p->base_reachable_time; - t->neigh_vars[NEIGH_VAR_DELAY_PROBE_TIME].data = &p->delay_probe_time; - t->neigh_vars[NEIGH_VAR_GC_STALETIME].data = &p->gc_staletime; - t->neigh_vars[NEIGH_VAR_QUEUE_LEN].data = &p->queue_len_bytes; - t->neigh_vars[NEIGH_VAR_QUEUE_LEN_BYTES].data = &p->queue_len_bytes; - t->neigh_vars[NEIGH_VAR_PROXY_QLEN].data = &p->proxy_qlen; - t->neigh_vars[NEIGH_VAR_ANYCAST_DELAY].data = &p->anycast_delay; - t->neigh_vars[NEIGH_VAR_PROXY_DELAY].data = &p->proxy_delay; - t->neigh_vars[NEIGH_VAR_LOCKTIME].data = &p->locktime; - t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].data = &p->retrans_time; - t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].data = &p->base_reachable_time; + for (i = 0; i < ARRAY_SIZE(t->neigh_vars); i++) { + t->neigh_vars[i].data += (long) p; + t->neigh_vars[i].extra1 = dev; + t->neigh_vars[i].extra2 = p; + } if (dev) { dev_name_source = dev->name; @@ -2990,26 +3065,32 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = (int *)(p + 1) + 3; } - if (handler) { /* RetransTime */ t->neigh_vars[NEIGH_VAR_RETRANS_TIME].proc_handler = handler; - t->neigh_vars[NEIGH_VAR_RETRANS_TIME].extra1 = dev; /* ReachableTime */ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = handler; - t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].extra1 = dev; /* RetransTime (in milliseconds)*/ t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler; - t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].extra1 = dev; /* ReachableTime (in milliseconds) */ t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler; - t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].extra1 = dev; } /* Don't export sysctls to unprivileged users */ if (neigh_parms_net(p)->user_ns != &init_user_ns) t->neigh_vars[0].procname = NULL; + switch (neigh_parms_family(p)) { + case AF_INET: + p_name = "ipv4"; + break; + case AF_INET6: + p_name = "ipv6"; + break; + default: + BUG(); + } + snprintf(neigh_path, sizeof(neigh_path), "net/%s/neigh/%s", p_name, dev_name_source); t->sysctl_header = diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index f3edf9635e02..93886246a0b4 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -498,17 +498,7 @@ static struct attribute_group wireless_group = { #define net_class_groups NULL #endif /* CONFIG_SYSFS */ -#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); -}; +#ifdef CONFIG_SYSFS #define to_rx_queue_attr(_attr) container_of(_attr, \ struct rx_queue_attribute, attr) @@ -543,6 +533,7 @@ static const struct sysfs_ops rx_queue_sysfs_ops = { .store = rx_queue_attr_store, }; +#ifdef CONFIG_RPS static ssize_t show_rps_map(struct netdev_rx_queue *queue, struct rx_queue_attribute *attribute, char *buf) { @@ -676,8 +667,8 @@ static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, while ((mask | (mask >> 1)) != mask) mask |= (mask >> 1); /* On 64 bit arches, must check mask fits in table->mask (u32), - * and on 32bit arches, must check RPS_DEV_FLOW_TABLE_SIZE(mask + 1) - * doesnt overflow. + * and on 32bit arches, must check + * RPS_DEV_FLOW_TABLE_SIZE(mask + 1) doesn't overflow. */ #if BITS_PER_LONG > 32 if (mask > (unsigned long)(u32)mask) @@ -718,16 +709,20 @@ static struct rx_queue_attribute rps_cpus_attribute = 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); +#endif /* CONFIG_RPS */ static struct attribute *rx_queue_default_attrs[] = { +#ifdef CONFIG_RPS &rps_cpus_attribute.attr, &rps_dev_flow_table_cnt_attribute.attr, +#endif NULL }; static void rx_queue_release(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); +#ifdef CONFIG_RPS struct rps_map *map; struct rps_dev_flow_table *flow_table; @@ -743,15 +738,29 @@ static void rx_queue_release(struct kobject *kobj) RCU_INIT_POINTER(queue->rps_flow_table, NULL); call_rcu(&flow_table->rcu, rps_dev_flow_table_release); } +#endif memset(kobj, 0, sizeof(*kobj)); dev_put(queue->dev); } +static const void *rx_queue_namespace(struct kobject *kobj) +{ + struct netdev_rx_queue *queue = to_rx_queue(kobj); + struct device *dev = &queue->dev->dev; + const void *ns = NULL; + + if (dev->class && dev->class->ns_type) + ns = dev->class->namespace(dev); + + return ns; +} + static struct kobj_type rx_queue_ktype = { .sysfs_ops = &rx_queue_sysfs_ops, .release = rx_queue_release, .default_attrs = rx_queue_default_attrs, + .namespace = rx_queue_namespace }; static int rx_queue_add_kobject(struct net_device *net, int index) @@ -763,25 +772,36 @@ static int rx_queue_add_kobject(struct net_device *net, int index) 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; + if (error) + goto exit; + + if (net->sysfs_rx_queue_group) { + error = sysfs_create_group(kobj, net->sysfs_rx_queue_group); + if (error) + goto exit; } kobject_uevent(kobj, KOBJ_ADD); dev_hold(queue->dev); return error; +exit: + kobject_put(kobj); + return error; } -#endif /* CONFIG_RPS */ +#endif /* CONFIG_SYFS */ int net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) { -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS int i; int error = 0; +#ifndef CONFIG_RPS + if (!net->sysfs_rx_queue_group) + return 0; +#endif for (i = old_num; i < new_num; i++) { error = rx_queue_add_kobject(net, i); if (error) { @@ -790,8 +810,12 @@ net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) } } - while (--i >= new_num) + while (--i >= new_num) { + if (net->sysfs_rx_queue_group) + sysfs_remove_group(&net->_rx[i].kobj, + net->sysfs_rx_queue_group); kobject_put(&net->_rx[i].kobj); + } return error; #else @@ -1082,10 +1106,23 @@ static void netdev_queue_release(struct kobject *kobj) dev_put(queue->dev); } +static const void *netdev_queue_namespace(struct kobject *kobj) +{ + struct netdev_queue *queue = to_netdev_queue(kobj); + struct device *dev = &queue->dev->dev; + const void *ns = NULL; + + if (dev->class && dev->class->ns_type) + ns = dev->class->namespace(dev); + + return ns; +} + static struct kobj_type netdev_queue_ktype = { .sysfs_ops = &netdev_queue_sysfs_ops, .release = netdev_queue_release, .default_attrs = netdev_queue_default_attrs, + .namespace = netdev_queue_namespace, }; static int netdev_queue_add_kobject(struct net_device *net, int index) @@ -1155,9 +1192,6 @@ static int register_queue_kobjects(struct net_device *net) NULL, &net->dev.kobj); if (!net->queues_kset) return -ENOMEM; -#endif - -#ifdef CONFIG_RPS real_rx = net->real_num_rx_queues; #endif real_tx = net->real_num_tx_queues; @@ -1184,7 +1218,7 @@ static void remove_queue_kobjects(struct net_device *net) { int real_rx = 0, real_tx = 0; -#ifdef CONFIG_RPS +#ifdef CONFIG_SYSFS real_rx = net->real_num_rx_queues; #endif real_tx = net->real_num_tx_queues; @@ -1358,7 +1392,7 @@ void netdev_class_remove_file_ns(struct class_attribute *class_attr, } EXPORT_SYMBOL(netdev_class_remove_file_ns); -int netdev_kobject_init(void) +int __init netdev_kobject_init(void) { kobj_ns_type_register(&net_ns_type_operations); return class_register(&net_class); diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h index bd7751ec1c4d..2745a1b51e03 100644 --- a/net/core/net-sysfs.h +++ b/net/core/net-sysfs.h @@ -1,7 +1,7 @@ #ifndef __NET_SYSFS_H__ #define __NET_SYSFS_H__ -int netdev_kobject_init(void); +int __init netdev_kobject_init(void); int netdev_register_kobject(struct net_device *); void netdev_unregister_kobject(struct net_device *); int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num); diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c new file mode 100644 index 000000000000..719efd541668 --- /dev/null +++ b/net/core/netclassid_cgroup.c @@ -0,0 +1,120 @@ +/* + * net/core/netclassid_cgroup.c Classid Cgroupfs Handling + * + * 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. + * + * Authors: Thomas Graf <tgraf@suug.ch> + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/cgroup.h> +#include <linux/fdtable.h> +#include <net/cls_cgroup.h> +#include <net/sock.h> + +static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct cgroup_cls_state, css) : NULL; +} + +struct cgroup_cls_state *task_cls_state(struct task_struct *p) +{ + return css_cls_state(task_css(p, net_cls_subsys_id)); +} +EXPORT_SYMBOL_GPL(task_cls_state); + +static struct cgroup_subsys_state * +cgrp_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct cgroup_cls_state *cs; + + cs = kzalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) + return ERR_PTR(-ENOMEM); + + return &cs->css; +} + +static int cgrp_css_online(struct cgroup_subsys_state *css) +{ + struct cgroup_cls_state *cs = css_cls_state(css); + struct cgroup_cls_state *parent = css_cls_state(css_parent(css)); + + if (parent) + cs->classid = parent->classid; + + return 0; +} + +static void cgrp_css_free(struct cgroup_subsys_state *css) +{ + kfree(css_cls_state(css)); +} + +static int update_classid(const void *v, struct file *file, unsigned n) +{ + int err; + struct socket *sock = sock_from_file(file, &err); + + if (sock) + sock->sk->sk_classid = (u32)(unsigned long)v; + + return 0; +} + +static void cgrp_attach(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset) +{ + struct cgroup_cls_state *cs = css_cls_state(css); + void *v = (void *)(unsigned long)cs->classid; + struct task_struct *p; + + cgroup_taskset_for_each(p, css, tset) { + task_lock(p); + iterate_fd(p->files, 0, update_classid, v); + task_unlock(p); + } +} + +static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft) +{ + return css_cls_state(css)->classid; +} + +static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, + u64 value) +{ + css_cls_state(css)->classid = (u32) value; + + return 0; +} + +static struct cftype ss_files[] = { + { + .name = "classid", + .read_u64 = read_classid, + .write_u64 = write_classid, + }, + { } /* terminate */ +}; + +struct cgroup_subsys net_cls_subsys = { + .name = "net_cls", + .css_alloc = cgrp_css_alloc, + .css_online = cgrp_css_online, + .css_free = cgrp_css_free, + .attach = cgrp_attach, + .subsys_id = net_cls_subsys_id, + .base_cftypes = ss_files, + .module = THIS_MODULE, +}; + +static int __init init_netclassid_cgroup(void) +{ + return cgroup_load_subsys(&net_cls_subsys); +} +__initcall(init_netclassid_cgroup); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 19fe9c717ced..c03f3dec4763 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -520,8 +520,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) skb->protocol = eth->h_proto = htons(ETH_P_IP); } - memcpy(eth->h_source, np->dev->dev_addr, ETH_ALEN); - memcpy(eth->h_dest, np->remote_mac, ETH_ALEN); + ether_addr_copy(eth->h_source, np->dev->dev_addr); + ether_addr_copy(eth->h_dest, np->remote_mac); skb->dev = np->dev; diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 56cbb69ba024..9043caedcd08 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -30,7 +30,7 @@ #define PRIOMAP_MIN_SZ 128 /* - * Extend @dev->priomap so that it's large enough to accomodate + * Extend @dev->priomap so that it's large enough to accommodate * @target_idx. @dev->priomap.priomap_len > @target_idx after successful * return. Must be called under rtnl lock. */ diff --git a/net/core/pktgen.c b/net/core/pktgen.c index a797fff7f222..fdac61cac1bd 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -389,6 +389,9 @@ struct pktgen_dev { #ifdef CONFIG_XFRM __u8 ipsmode; /* IPSEC mode (config) */ __u8 ipsproto; /* IPSEC type (config) */ + __u32 spi; + struct dst_entry dst; + struct dst_ops dstops; #endif char result[512]; }; @@ -654,8 +657,11 @@ static int pktgen_if_show(struct seq_file *seq, void *v) } #ifdef CONFIG_XFRM - if (pkt_dev->flags & F_IPSEC_ON) + if (pkt_dev->flags & F_IPSEC_ON) { seq_printf(seq, "IPSEC "); + if (pkt_dev->spi) + seq_printf(seq, "spi:%u", pkt_dev->spi); + } #endif if (pkt_dev->flags & F_MACSRC_RND) @@ -1434,7 +1440,7 @@ static ssize_t pktgen_if_write(struct file *file, if (!mac_pton(valstr, pkt_dev->dst_mac)) return -EINVAL; /* Set up Dest MAC */ - memcpy(&pkt_dev->hh[0], pkt_dev->dst_mac, ETH_ALEN); + ether_addr_copy(&pkt_dev->hh[0], pkt_dev->dst_mac); sprintf(pg_result, "OK: dstmac %pM", pkt_dev->dst_mac); return count; @@ -1451,7 +1457,7 @@ static ssize_t pktgen_if_write(struct file *file, if (!mac_pton(valstr, pkt_dev->src_mac)) return -EINVAL; /* Set up Src MAC */ - memcpy(&pkt_dev->hh[6], pkt_dev->src_mac, ETH_ALEN); + ether_addr_copy(&pkt_dev->hh[6], pkt_dev->src_mac); sprintf(pg_result, "OK: srcmac %pM", pkt_dev->src_mac); return count; @@ -1476,7 +1482,18 @@ static ssize_t pktgen_if_write(struct file *file, sprintf(pg_result, "OK: flows=%u", pkt_dev->cflows); return count; } +#ifdef CONFIG_XFRM + if (!strcmp(name, "spi")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + i += len; + pkt_dev->spi = value; + sprintf(pg_result, "OK: spi=%u", pkt_dev->spi); + return count; + } +#endif if (!strcmp(name, "flowlen")) { len = num_arg(&user_buffer[i], 10, &value); if (len < 0) @@ -2043,10 +2060,10 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) /* Default to the interface's mac if not explicitly set. */ if (is_zero_ether_addr(pkt_dev->src_mac)) - memcpy(&(pkt_dev->hh[6]), pkt_dev->odev->dev_addr, ETH_ALEN); + ether_addr_copy(&(pkt_dev->hh[6]), pkt_dev->odev->dev_addr); /* Set up Dest MAC */ - memcpy(&(pkt_dev->hh[0]), pkt_dev->dst_mac, ETH_ALEN); + ether_addr_copy(&(pkt_dev->hh[0]), pkt_dev->dst_mac); if (pkt_dev->flags & F_IPV6) { int i, set = 0, err = 1; @@ -2233,13 +2250,21 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) struct xfrm_state *x = pkt_dev->flows[flow].x; struct pktgen_net *pn = net_generic(dev_net(pkt_dev->odev), pg_net_id); if (!x) { - /*slow path: we dont already have xfrm_state*/ - x = xfrm_stateonly_find(pn->net, DUMMY_MARK, - (xfrm_address_t *)&pkt_dev->cur_daddr, - (xfrm_address_t *)&pkt_dev->cur_saddr, - AF_INET, - pkt_dev->ipsmode, - pkt_dev->ipsproto, 0); + + if (pkt_dev->spi) { + /* We need as quick as possible to find the right SA + * Searching with minimum criteria to archieve this. + */ + x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET); + } else { + /* slow path: we dont already have xfrm_state */ + x = xfrm_stateonly_find(pn->net, DUMMY_MARK, + (xfrm_address_t *)&pkt_dev->cur_daddr, + (xfrm_address_t *)&pkt_dev->cur_saddr, + AF_INET, + pkt_dev->ipsmode, + pkt_dev->ipsproto, 0); + } if (x) { pkt_dev->flows[flow].x = x; set_pkt_overhead(pkt_dev); @@ -2475,31 +2500,47 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) #ifdef CONFIG_XFRM +static u32 pktgen_dst_metrics[RTAX_MAX + 1] = { + + [RTAX_HOPLIMIT] = 0x5, /* Set a static hoplimit */ +}; + static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev) { struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x; int err = 0; + struct net *net = dev_net(pkt_dev->odev); if (!x) return 0; /* XXX: we dont support tunnel mode for now until * we resolve the dst issue */ - if (x->props.mode != XFRM_MODE_TRANSPORT) + if ((x->props.mode != XFRM_MODE_TRANSPORT) && (pkt_dev->spi == 0)) return 0; - spin_lock(&x->lock); + /* But when user specify an valid SPI, transformation + * supports both transport/tunnel mode + ESP/AH type. + */ + if ((x->props.mode == XFRM_MODE_TUNNEL) && (pkt_dev->spi != 0)) + skb->_skb_refdst = (unsigned long)&pkt_dev->dst | SKB_DST_NOREF; + rcu_read_lock_bh(); err = x->outer_mode->output(x, skb); - if (err) + rcu_read_unlock_bh(); + if (err) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR); goto error; + } err = x->type->output(x, skb); - if (err) + if (err) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR); goto error; - + } + spin_lock_bh(&x->lock); x->curlft.bytes += skb->len; x->curlft.packets++; + spin_unlock_bh(&x->lock); error: - spin_unlock(&x->lock); return err; } @@ -3542,6 +3583,17 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) #ifdef CONFIG_XFRM pkt_dev->ipsmode = XFRM_MODE_TRANSPORT; pkt_dev->ipsproto = IPPROTO_ESP; + + /* xfrm tunnel mode needs additional dst to extract outter + * ip header protocol/ttl/id field, here creat a phony one. + * instead of looking for a valid rt, which definitely hurting + * performance under such circumstance. + */ + pkt_dev->dstops.family = AF_INET; + pkt_dev->dst.dev = pkt_dev->odev; + dst_init_metrics(&pkt_dev->dst, pktgen_dst_metrics, false); + pkt_dev->dst.child = &pkt_dev->dst; + pkt_dev->dst.ops = &pkt_dev->dstops; #endif return add_dev_to_thread(t, pkt_dev); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index cf67144d3e3c..393b1bc9a618 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -365,6 +365,22 @@ void rtnl_link_unregister(struct rtnl_link_ops *ops) } EXPORT_SYMBOL_GPL(rtnl_link_unregister); +static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev) +{ + struct net_device *master_dev; + const struct rtnl_link_ops *ops; + + master_dev = netdev_master_upper_dev_get((struct net_device *) dev); + if (!master_dev) + return 0; + ops = master_dev->rtnl_link_ops; + if (!ops->get_slave_size) + return 0; + /* IFLA_INFO_SLAVE_DATA + nested data */ + return nla_total_size(sizeof(struct nlattr)) + + ops->get_slave_size(master_dev, dev); +} + static size_t rtnl_link_get_size(const struct net_device *dev) { const struct rtnl_link_ops *ops = dev->rtnl_link_ops; @@ -385,6 +401,8 @@ static size_t rtnl_link_get_size(const struct net_device *dev) /* IFLA_INFO_XSTATS */ size += nla_total_size(ops->get_xstats_size(dev)); + size += rtnl_link_get_slave_info_data_size(dev); + return size; } @@ -403,34 +421,16 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family) } /** - * __rtnl_af_register - Register rtnl_af_ops with rtnetlink. - * @ops: struct rtnl_af_ops * to register - * - * The caller must hold the rtnl_mutex. - * - * Returns 0 on success or a negative error code. - */ -int __rtnl_af_register(struct rtnl_af_ops *ops) -{ - list_add_tail(&ops->list, &rtnl_af_ops); - return 0; -} -EXPORT_SYMBOL_GPL(__rtnl_af_register); - -/** * rtnl_af_register - Register rtnl_af_ops with rtnetlink. * @ops: struct rtnl_af_ops * to register * * Returns 0 on success or a negative error code. */ -int rtnl_af_register(struct rtnl_af_ops *ops) +void rtnl_af_register(struct rtnl_af_ops *ops) { - int err; - rtnl_lock(); - err = __rtnl_af_register(ops); + list_add_tail(&ops->list, &rtnl_af_ops); rtnl_unlock(); - return err; } EXPORT_SYMBOL_GPL(rtnl_af_register); @@ -477,40 +477,100 @@ static size_t rtnl_link_get_af_size(const struct net_device *dev) return size; } -static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev) +static bool rtnl_have_link_slave_info(const struct net_device *dev) { - const struct rtnl_link_ops *ops = dev->rtnl_link_ops; - struct nlattr *linkinfo, *data; - int err = -EMSGSIZE; + struct net_device *master_dev; - linkinfo = nla_nest_start(skb, IFLA_LINKINFO); - if (linkinfo == NULL) - goto out; + master_dev = netdev_master_upper_dev_get((struct net_device *) dev); + if (master_dev && master_dev->rtnl_link_ops) + return true; + return false; +} + +static int rtnl_link_slave_info_fill(struct sk_buff *skb, + const struct net_device *dev) +{ + struct net_device *master_dev; + const struct rtnl_link_ops *ops; + struct nlattr *slave_data; + int err; + + master_dev = netdev_master_upper_dev_get((struct net_device *) dev); + if (!master_dev) + return 0; + ops = master_dev->rtnl_link_ops; + if (!ops) + return 0; + if (nla_put_string(skb, IFLA_INFO_SLAVE_KIND, ops->kind) < 0) + return -EMSGSIZE; + if (ops->fill_slave_info) { + slave_data = nla_nest_start(skb, IFLA_INFO_SLAVE_DATA); + if (!slave_data) + return -EMSGSIZE; + err = ops->fill_slave_info(skb, master_dev, dev); + if (err < 0) + goto err_cancel_slave_data; + nla_nest_end(skb, slave_data); + } + return 0; + +err_cancel_slave_data: + nla_nest_cancel(skb, slave_data); + return err; +} + +static int rtnl_link_info_fill(struct sk_buff *skb, + const struct net_device *dev) +{ + const struct rtnl_link_ops *ops = dev->rtnl_link_ops; + struct nlattr *data; + int err; + if (!ops) + return 0; if (nla_put_string(skb, IFLA_INFO_KIND, ops->kind) < 0) - goto err_cancel_link; + return -EMSGSIZE; if (ops->fill_xstats) { err = ops->fill_xstats(skb, dev); if (err < 0) - goto err_cancel_link; + return err; } if (ops->fill_info) { data = nla_nest_start(skb, IFLA_INFO_DATA); - if (data == NULL) { - err = -EMSGSIZE; - goto err_cancel_link; - } + if (data == NULL) + return -EMSGSIZE; err = ops->fill_info(skb, dev); if (err < 0) goto err_cancel_data; nla_nest_end(skb, data); } - - nla_nest_end(skb, linkinfo); return 0; err_cancel_data: nla_nest_cancel(skb, data); + return err; +} + +static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev) +{ + struct nlattr *linkinfo; + int err = -EMSGSIZE; + + linkinfo = nla_nest_start(skb, IFLA_LINKINFO); + if (linkinfo == NULL) + goto out; + + err = rtnl_link_info_fill(skb, dev); + if (err < 0) + goto err_cancel_link; + + err = rtnl_link_slave_info_fill(skb, dev); + if (err < 0) + goto err_cancel_link; + + nla_nest_end(skb, linkinfo); + return 0; + err_cancel_link: nla_nest_cancel(skb, linkinfo); out: @@ -1019,7 +1079,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (rtnl_port_fill(skb, dev)) goto nla_put_failure; - if (dev->rtnl_link_ops) { + if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) { if (rtnl_link_fill(skb, dev) < 0) goto nla_put_failure; } @@ -1142,6 +1202,8 @@ EXPORT_SYMBOL(ifla_policy); static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { [IFLA_INFO_KIND] = { .type = NLA_STRING }, [IFLA_INFO_DATA] = { .type = NLA_NESTED }, + [IFLA_INFO_SLAVE_KIND] = { .type = NLA_STRING }, + [IFLA_INFO_SLAVE_DATA] = { .type = NLA_NESTED }, }; static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = { @@ -1729,7 +1791,9 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); const struct rtnl_link_ops *ops; + const struct rtnl_link_ops *m_ops = NULL; struct net_device *dev; + struct net_device *master_dev = NULL; struct ifinfomsg *ifm; char kind[MODULE_NAME_LEN]; char ifname[IFNAMSIZ]; @@ -1759,6 +1823,12 @@ replay: dev = NULL; } + if (dev) { + master_dev = netdev_master_upper_dev_get(dev); + if (master_dev) + m_ops = master_dev->rtnl_link_ops; + } + err = validate_linkmsg(dev, tb); if (err < 0) return err; @@ -1780,7 +1850,10 @@ replay: } if (1) { - struct nlattr *attr[ops ? ops->maxtype + 1 : 0], **data = NULL; + struct nlattr *attr[ops ? ops->maxtype + 1 : 0]; + struct nlattr *slave_attr[m_ops ? m_ops->slave_maxtype + 1 : 0]; + struct nlattr **data = NULL; + struct nlattr **slave_data = NULL; struct net *dest_net; if (ops) { @@ -1799,6 +1872,24 @@ replay: } } + if (m_ops) { + if (m_ops->slave_maxtype && + linkinfo[IFLA_INFO_SLAVE_DATA]) { + err = nla_parse_nested(slave_attr, + m_ops->slave_maxtype, + linkinfo[IFLA_INFO_SLAVE_DATA], + m_ops->slave_policy); + if (err < 0) + return err; + slave_data = slave_attr; + } + if (m_ops->slave_validate) { + err = m_ops->slave_validate(tb, slave_data); + if (err < 0) + return err; + } + } + if (dev) { int modified = 0; @@ -1818,6 +1909,17 @@ replay: modified = 1; } + if (linkinfo[IFLA_INFO_SLAVE_DATA]) { + if (!m_ops || !m_ops->slave_changelink) + return -EOPNOTSUPP; + + err = m_ops->slave_changelink(master_dev, dev, + tb, slave_data); + if (err < 0) + return err; + modified = 1; + } + return do_setlink(dev, ifm, tb, ifname, modified); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 0b5149c5bc4a..8f519dbb358b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -65,6 +65,7 @@ #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> +#include <net/ip6_checksum.h> #include <net/xfrm.h> #include <asm/uaccess.h> @@ -682,9 +683,8 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->inner_network_header = old->inner_network_header; new->inner_mac_header = old->inner_mac_header; skb_dst_copy(new, old); - new->rxhash = old->rxhash; + skb_copy_hash(new, old); new->ooo_okay = old->ooo_okay; - new->l4_rxhash = old->l4_rxhash; new->no_fcs = old->no_fcs; new->encapsulation = old->encapsulation; #ifdef CONFIG_XFRM @@ -2092,6 +2092,91 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, } EXPORT_SYMBOL(skb_copy_and_csum_bits); + /** + * skb_zerocopy_headlen - Calculate headroom needed for skb_zerocopy() + * @from: source buffer + * + * Calculates the amount of linear headroom needed in the 'to' skb passed + * into skb_zerocopy(). + */ +unsigned int +skb_zerocopy_headlen(const struct sk_buff *from) +{ + unsigned int hlen = 0; + + if (!from->head_frag || + skb_headlen(from) < L1_CACHE_BYTES || + skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) + hlen = skb_headlen(from); + + if (skb_has_frag_list(from)) + hlen = from->len; + + return hlen; +} +EXPORT_SYMBOL_GPL(skb_zerocopy_headlen); + +/** + * skb_zerocopy - Zero copy skb to skb + * @to: destination buffer + * @source: source buffer + * @len: number of bytes to copy from source buffer + * @hlen: size of linear headroom in destination buffer + * + * Copies up to `len` bytes from `from` to `to` by creating references + * to the frags in the source buffer. + * + * The `hlen` as calculated by skb_zerocopy_headlen() specifies the + * headroom in the `to` buffer. + */ +void +skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen) +{ + int i, j = 0; + int plen = 0; /* length of skb->head fragment */ + struct page *page; + unsigned int offset; + + BUG_ON(!from->head_frag && !hlen); + + /* dont bother with small payloads */ + if (len <= skb_tailroom(to)) { + skb_copy_bits(from, 0, skb_put(to, len), len); + return; + } + + if (hlen) { + skb_copy_bits(from, 0, skb_put(to, hlen), hlen); + len -= hlen; + } else { + plen = min_t(int, skb_headlen(from), len); + if (plen) { + page = virt_to_head_page(from->head); + offset = from->data - (unsigned char *)page_address(page); + __skb_fill_page_desc(to, 0, page, offset, plen); + get_page(page); + j = 1; + len -= plen; + } + } + + to->truesize += len + plen; + to->len += len + plen; + to->data_len += len + plen; + + for (i = 0; i < skb_shinfo(from)->nr_frags; i++) { + if (!len) + break; + skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i]; + skb_shinfo(to)->frags[j].size = min_t(int, skb_shinfo(to)->frags[j].size, len); + len -= skb_shinfo(to)->frags[j].size; + skb_frag_ref(to, j); + j++; + } + skb_shinfo(to)->nr_frags = j; +} +EXPORT_SYMBOL_GPL(skb_zerocopy); + void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) { __wsum csum; @@ -2952,10 +3037,7 @@ perform_csum_check: return segs; err: - while ((skb = segs)) { - segs = skb->next; - kfree_skb(skb); - } + kfree_skb_list(segs); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(skb_segment); @@ -3438,6 +3520,278 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) } EXPORT_SYMBOL_GPL(skb_partial_csum_set); +static int skb_maybe_pull_tail(struct sk_buff *skb, unsigned int len, + unsigned int max) +{ + if (skb_headlen(skb) >= len) + return 0; + + /* If we need to pullup then pullup to the max, so we + * won't need to do it again. + */ + if (max > skb->len) + max = skb->len; + + if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL) + return -ENOMEM; + + if (skb_headlen(skb) < len) + return -EPROTO; + + return 0; +} + +/* This value should be large enough to cover a tagged ethernet header plus + * maximally sized IP and TCP or UDP headers. + */ +#define MAX_IP_HDR_LEN 128 + +static int skb_checksum_setup_ip(struct sk_buff *skb, bool recalculate) +{ + unsigned int off; + bool fragment; + int err; + + fragment = false; + + err = skb_maybe_pull_tail(skb, + sizeof(struct iphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF)) + fragment = true; + + off = ip_hdrlen(skb); + + err = -EPROTO; + + if (fragment) + goto out; + + switch (ip_hdr(skb)->protocol) { + case IPPROTO_TCP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct tcphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct tcphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + tcp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + IPPROTO_TCP, 0); + break; + case IPPROTO_UDP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct udphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct udphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + udp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + IPPROTO_UDP, 0); + break; + default: + goto out; + } + + err = 0; + +out: + return err; +} + +/* This value should be large enough to cover a tagged ethernet header plus + * an IPv6 header, all options, and a maximal TCP or UDP header. + */ +#define MAX_IPV6_HDR_LEN 256 + +#define OPT_HDR(type, skb, off) \ + (type *)(skb_network_header(skb) + (off)) + +static int skb_checksum_setup_ipv6(struct sk_buff *skb, bool recalculate) +{ + int err; + u8 nexthdr; + unsigned int off; + unsigned int len; + bool fragment; + bool done; + + fragment = false; + done = false; + + off = sizeof(struct ipv6hdr); + + err = skb_maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + nexthdr = ipv6_hdr(skb)->nexthdr; + + len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); + while (off <= len && !done) { + switch (nexthdr) { + case IPPROTO_DSTOPTS: + case IPPROTO_HOPOPTS: + case IPPROTO_ROUTING: { + struct ipv6_opt_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct ipv6_opt_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ipv6_opt_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_optlen(hp); + break; + } + case IPPROTO_AH: { + struct ip_auth_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct ip_auth_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ip_auth_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_authlen(hp); + break; + } + case IPPROTO_FRAGMENT: { + struct frag_hdr *hp; + + err = skb_maybe_pull_tail(skb, + off + + sizeof(struct frag_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct frag_hdr, skb, off); + + if (hp->frag_off & htons(IP6_OFFSET | IP6_MF)) + fragment = true; + + nexthdr = hp->nexthdr; + off += sizeof(struct frag_hdr); + break; + } + default: + done = true; + break; + } + } + + err = -EPROTO; + + if (!done || fragment) + goto out; + + switch (nexthdr) { + case IPPROTO_TCP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct tcphdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct tcphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + tcp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, + IPPROTO_TCP, 0); + break; + case IPPROTO_UDP: + err = skb_maybe_pull_tail(skb, + off + sizeof(struct udphdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct udphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate) + udp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, + IPPROTO_UDP, 0); + break; + default: + goto out; + } + + err = 0; + +out: + return err; +} + +/** + * skb_checksum_setup - set up partial checksum offset + * @skb: the skb to set up + * @recalculate: if true the pseudo-header checksum will be recalculated + */ +int skb_checksum_setup(struct sk_buff *skb, bool recalculate) +{ + int err; + + switch (skb->protocol) { + case htons(ETH_P_IP): + err = skb_checksum_setup_ip(skb, recalculate); + break; + + case htons(ETH_P_IPV6): + err = skb_checksum_setup_ipv6(skb, recalculate); + break; + + default: + err = -EPROTO; + break; + } + + return err; +} +EXPORT_SYMBOL(skb_checksum_setup); + void __skb_warn_lro_forwarding(const struct sk_buff *skb) { net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n", diff --git a/net/core/sock.c b/net/core/sock.c index 5393b4b719d7..0c127dcdf6a8 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -925,8 +925,8 @@ set_rcvbuf: EXPORT_SYMBOL(sock_setsockopt); -void cred_to_ucred(struct pid *pid, const struct cred *cred, - struct ucred *ucred) +static void cred_to_ucred(struct pid *pid, const struct cred *cred, + struct ucred *ucred) { ucred->pid = pid_vnr(pid); ucred->uid = ucred->gid = -1; @@ -937,7 +937,6 @@ void cred_to_ucred(struct pid *pid, const struct cred *cred, ucred->gid = from_kgid_munged(current_ns, cred->egid); } } -EXPORT_SYMBOL_GPL(cred_to_ucred); int sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) @@ -1168,6 +1167,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sock_flag(sk, SOCK_FILTER_LOCKED); break; + case SO_BPF_EXTENSIONS: + v.val = bpf_tell_extensions(); + break; + case SO_SELECT_ERR_QUEUE: v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE); break; @@ -1308,19 +1311,7 @@ static void sk_prot_free(struct proto *prot, struct sock *sk) module_put(owner); } -#if IS_ENABLED(CONFIG_NET_CLS_CGROUP) -void sock_update_classid(struct sock *sk) -{ - u32 classid; - - classid = task_cls_classid(current); - if (classid != sk->sk_classid) - sk->sk_classid = classid; -} -EXPORT_SYMBOL(sock_update_classid); -#endif - -#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) void sock_update_netprioidx(struct sock *sk) { if (in_interrupt()) @@ -1666,22 +1657,6 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, EXPORT_SYMBOL(sock_wmalloc); /* - * Allocate a skb from the socket's receive buffer. - */ -struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force, - gfp_t priority) -{ - if (force || atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { - struct sk_buff *skb = alloc_skb(size, priority); - if (skb) { - skb_set_owner_r(skb, sk); - return skb; - } - } - return NULL; -} - -/* * Allocate a memory block from the socket's option memory buffer. */ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) @@ -1865,9 +1840,7 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio) put_page(pfrag->page); } - /* We restrict high order allocations to users that can afford to wait */ - order = (prio & __GFP_WAIT) ? SKB_FRAG_PAGE_ORDER : 0; - + order = SKB_FRAG_PAGE_ORDER; do { gfp_t gfp = prio; diff --git a/net/core/stream.c b/net/core/stream.c index 512f0a24269b..301c05f26060 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -122,7 +122,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) DEFINE_WAIT(wait); if (sk_stream_memory_free(sk)) - current_timeo = vm_wait = (net_random() % (HZ / 5)) + 2; + current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2; while (1) { set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index cca444190907..cf9cd13509a7 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -122,7 +122,8 @@ static int flow_limit_cpu_sysctl(struct ctl_table *table, int write, synchronize_rcu(); kfree(cur); } else if (!cur && cpumask_test_cpu(i, mask)) { - cur = kzalloc(len, GFP_KERNEL); + cur = kzalloc_node(len, GFP_KERNEL, + cpu_to_node(i)); if (!cur) { /* not unwinding previous changes */ ret = -ENOMEM; |