diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/datagram.c | 45 | ||||
-rw-r--r-- | net/core/dev.c | 229 | ||||
-rw-r--r-- | net/core/dst.c | 16 | ||||
-rw-r--r-- | net/core/ethtool.c | 2 | ||||
-rw-r--r-- | net/core/fib_rules.c | 14 | ||||
-rw-r--r-- | net/core/filter.c | 6 | ||||
-rw-r--r-- | net/core/gen_stats.c | 15 | ||||
-rw-r--r-- | net/core/iovec.c | 10 | ||||
-rw-r--r-- | net/core/neighbour.c | 17 | ||||
-rw-r--r-- | net/core/net_namespace.c | 2 | ||||
-rw-r--r-- | net/core/netpoll.c | 2 | ||||
-rw-r--r-- | net/core/pktgen.c | 20 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 271 | ||||
-rw-r--r-- | net/core/secure_seq.c | 25 | ||||
-rw-r--r-- | net/core/skbuff.c | 121 | ||||
-rw-r--r-- | net/core/sock.c | 72 | ||||
-rw-r--r-- | net/core/sock_diag.c | 4 | ||||
-rw-r--r-- | net/core/sysctl_net_core.c | 10 | ||||
-rw-r--r-- | net/core/utils.c | 8 |
19 files changed, 657 insertions, 232 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c index a16ed7bbe376..13bc7dad7990 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -130,6 +130,35 @@ out_noerr: goto out; } +static struct sk_buff *skb_set_peeked(struct sk_buff *skb) +{ + struct sk_buff *nskb; + + if (skb->peeked) + return skb; + + /* We have to unshare an skb before modifying it. */ + if (!skb_shared(skb)) + goto done; + + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return ERR_PTR(-ENOMEM); + + skb->prev->next = nskb; + skb->next->prev = nskb; + nskb->prev = skb->prev; + nskb->next = skb->next; + + consume_skb(skb); + skb = nskb; + +done: + skb->peeked = 1; + + return skb; +} + /** * __skb_recv_datagram - Receive a datagram skbuff * @sk: socket @@ -164,7 +193,9 @@ out_noerr: struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, int *peeked, int *off, int *err) { + struct sk_buff_head *queue = &sk->sk_receive_queue; struct sk_buff *skb, *last; + unsigned long cpu_flags; long timeo; /* * Caller is allowed not to check sk->sk_err before skb_recv_datagram() @@ -183,8 +214,6 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, * Look at current nfs client by the way... * However, this function was correct in any case. 8) */ - unsigned long cpu_flags; - struct sk_buff_head *queue = &sk->sk_receive_queue; int _off = *off; last = (struct sk_buff *)queue; @@ -198,7 +227,12 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, _off -= skb->len; continue; } - skb->peeked = 1; + + skb = skb_set_peeked(skb); + error = PTR_ERR(skb); + if (IS_ERR(skb)) + goto unlock_err; + atomic_inc(&skb->users); } else __skb_unlink(skb, queue); @@ -222,6 +256,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, return NULL; +unlock_err: + spin_unlock_irqrestore(&queue->lock, cpu_flags); no_packet: *err = error; return NULL; @@ -742,7 +778,8 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len) if (likely(!sum)) { if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) netdev_rx_csum_fault(skb->dev); - skb->ip_summed = CHECKSUM_UNNECESSARY; + if (!skb_shared(skb)) + skb->ip_summed = CHECKSUM_UNNECESSARY; } return sum; } diff --git a/net/core/dev.c b/net/core/dev.c index 45fa2f11f84d..ae3260fc133d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -148,6 +148,9 @@ 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); +static int call_netdevice_notifiers_info(unsigned long val, + struct net_device *dev, + struct netdev_notifier_info *info); /* * The @dev_base_head list is protected by @dev_base_lock and the rtnl @@ -937,7 +940,7 @@ bool dev_valid_name(const char *name) return false; while (*name) { - if (*name == '/' || isspace(*name)) + if (*name == '/' || *name == ':' || isspace(*name)) return false; name++; } @@ -1207,7 +1210,11 @@ EXPORT_SYMBOL(netdev_features_change); void netdev_state_change(struct net_device *dev) { if (dev->flags & IFF_UP) { - call_netdevice_notifiers(NETDEV_CHANGE, dev); + struct netdev_notifier_change_info change_info; + + change_info.flags_changed = 0; + call_netdevice_notifiers_info(NETDEV_CHANGE, dev, + &change_info.info); rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); } } @@ -1702,6 +1709,7 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) skb_scrub_packet(skb, true); skb->protocol = eth_type_trans(skb, dev); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); return netif_rx_internal(skb); } @@ -2289,7 +2297,7 @@ EXPORT_SYMBOL(skb_checksum_help); __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { __be16 type = skb->protocol; - int vlan_depth = ETH_HLEN; + int vlan_depth = skb->mac_len; /* Tunnel gso handlers can set protocol to ethernet. */ if (type == htons(ETH_P_TEB)) { @@ -2522,11 +2530,14 @@ netdev_features_t netif_skb_dev_features(struct sk_buff *skb, if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs) features &= ~NETIF_F_GSO_MASK; - if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { - struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; - protocol = veh->h_vlan_encapsulated_proto; - } else if (!vlan_tx_tag_present(skb)) { - return harmonize_features(skb, dev, features); + if (!vlan_tx_tag_present(skb)) { + if (unlikely(protocol == htons(ETH_P_8021Q) || + protocol == htons(ETH_P_8021AD))) { + struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; + protocol = veh->h_vlan_encapsulated_proto; + } else { + return harmonize_features(skb, dev, features); + } } features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | @@ -2764,7 +2775,9 @@ static void skb_update_prio(struct sk_buff *skb) #define skb_update_prio(skb) #endif -static DEFINE_PER_CPU(int, xmit_recursion); +DEFINE_PER_CPU(int, xmit_recursion); +EXPORT_SYMBOL(xmit_recursion); + #define RECURSION_LIMIT 10 /** @@ -3201,6 +3214,8 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, local_irq_save(flags); rps_lock(sd); + if (!netif_running(skb->dev)) + goto drop; qlen = skb_queue_len(&sd->input_pkt_queue); if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) { if (skb_queue_len(&sd->input_pkt_queue)) { @@ -3222,6 +3237,7 @@ enqueue: goto enqueue; } +drop: sd->dropped++; rps_unlock(sd); @@ -3538,8 +3554,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc) pt_prev = NULL; - rcu_read_lock(); - another_round: skb->skb_iif = skb->dev->ifindex; @@ -3547,9 +3561,9 @@ another_round: if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || skb->protocol == cpu_to_be16(ETH_P_8021AD)) { - skb = vlan_untag(skb); + skb = skb_vlan_untag(skb); if (unlikely(!skb)) - goto unlock; + goto out; } #ifdef CONFIG_NET_CLS_ACT @@ -3574,7 +3588,7 @@ skip_taps: #ifdef CONFIG_NET_CLS_ACT skb = handle_ing(skb, &pt_prev, &ret, orig_dev); if (!skb) - goto unlock; + goto out; ncls: #endif @@ -3589,7 +3603,7 @@ ncls: if (vlan_do_receive(&skb)) goto another_round; else if (unlikely(!skb)) - goto unlock; + goto out; } rx_handler = rcu_dereference(skb->dev->rx_handler); @@ -3601,7 +3615,7 @@ ncls: switch (rx_handler(&skb)) { case RX_HANDLER_CONSUMED: ret = NET_RX_SUCCESS; - goto unlock; + goto out; case RX_HANDLER_ANOTHER: goto another_round; case RX_HANDLER_EXACT: @@ -3653,8 +3667,6 @@ drop: ret = NET_RX_DROP; } -unlock: - rcu_read_unlock(); out: return ret; } @@ -3686,29 +3698,30 @@ static int __netif_receive_skb(struct sk_buff *skb) static int netif_receive_skb_internal(struct sk_buff *skb) { + int ret; + net_timestamp_check(netdev_tstamp_prequeue, skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; + rcu_read_lock(); + #ifdef CONFIG_RPS if (static_key_false(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; - int cpu, ret; - - rcu_read_lock(); - - cpu = get_rps_cpu(skb->dev, skb, &rflow); + int cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu >= 0) { ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); return ret; } - rcu_read_unlock(); } #endif - return __netif_receive_skb(skb); + ret = __netif_receive_skb(skb); + rcu_read_unlock(); + return ret; } /** @@ -3944,6 +3957,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff } NAPI_GRO_CB(skb)->count = 1; NAPI_GRO_CB(skb)->age = jiffies; + NAPI_GRO_CB(skb)->last = skb; skb_shinfo(skb)->gso_size = skb_gro_len(skb); skb->next = napi->gro_list; napi->gro_list = skb; @@ -4050,6 +4064,9 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->vlan_tci = 0; skb->dev = napi->dev; skb->skb_iif = 0; + skb->encapsulation = 0; + skb_shinfo(skb)->gso_type = 0; + skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); napi->skb = skb; } @@ -4165,8 +4182,10 @@ static int process_backlog(struct napi_struct *napi, int quota) unsigned int qlen; while ((skb = __skb_dequeue(&sd->process_queue))) { + rcu_read_lock(); local_irq_enable(); __netif_receive_skb(skb); + rcu_read_unlock(); local_irq_disable(); input_queue_head_incr(sd); if (++work >= quota) { @@ -4605,6 +4624,32 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); /** + * netdev_lower_get_next - Get the next device from the lower neighbour + * list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next netdev_adjacent from the dev's lower neighbour + * list, starting from iter position. The caller must hold RTNL lock or + * its own locking that guarantees that the neighbour lower + * list will remain unchainged. + */ +void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) +{ + struct netdev_adjacent *lower; + + lower = list_entry((*iter)->next, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; + + *iter = &lower->list; + + return lower->dev; +} +EXPORT_SYMBOL(netdev_lower_get_next); + +/** * netdev_lower_get_first_private_rcu - Get the first ->private from the * lower neighbour list, RCU * variant @@ -4664,9 +4709,14 @@ static void netdev_adjacent_sysfs_del(struct net_device *dev, 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 inline bool netdev_adjacent_is_neigh_list(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list) +{ + return (dev_list == &dev->adj_list.upper || + dev_list == &dev->adj_list.lower) && + net_eq(dev_net(dev), dev_net(adj_dev)); +} static int __netdev_adjacent_dev_insert(struct net_device *dev, struct net_device *adj_dev, @@ -4696,7 +4746,7 @@ 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 (netdev_adjacent_is_neigh_list(dev, dev_list)) { + if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) { ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list); if (ret) goto free_adj; @@ -4717,7 +4767,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, return 0; remove_symlinks: - if (netdev_adjacent_is_neigh_list(dev, dev_list)) + if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); free_adj: kfree(adj); @@ -4750,7 +4800,7 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, if (adj->master) sysfs_remove_link(&(dev->dev.kobj), "master"); - if (netdev_adjacent_is_neigh_list(dev, dev_list)) + if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); list_del_rcu(&adj->list); @@ -4855,7 +4905,7 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper)) return -EBUSY; - if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper)) + if (__netdev_find_adj(dev, upper_dev, &dev->adj_list.upper)) return -EEXIST; if (master && netdev_master_upper_dev_get(dev)) @@ -5020,11 +5070,65 @@ void netdev_upper_dev_unlink(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_dev_unlink); +void netdev_adjacent_add_links(struct net_device *dev) +{ + struct netdev_adjacent *iter; + + struct net *net = dev_net(dev); + + list_for_each_entry(iter, &dev->adj_list.upper, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.lower); + netdev_adjacent_sysfs_add(dev, iter->dev, + &dev->adj_list.upper); + } + + list_for_each_entry(iter, &dev->adj_list.lower, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.upper); + netdev_adjacent_sysfs_add(dev, iter->dev, + &dev->adj_list.lower); + } +} + +void netdev_adjacent_del_links(struct net_device *dev) +{ + struct netdev_adjacent *iter; + + struct net *net = dev_net(dev); + + list_for_each_entry(iter, &dev->adj_list.upper, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_del(iter->dev, dev->name, + &iter->dev->adj_list.lower); + netdev_adjacent_sysfs_del(dev, iter->dev->name, + &dev->adj_list.upper); + } + + list_for_each_entry(iter, &dev->adj_list.lower, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; + netdev_adjacent_sysfs_del(iter->dev, dev->name, + &iter->dev->adj_list.upper); + netdev_adjacent_sysfs_del(dev, iter->dev->name, + &dev->adj_list.lower); + } +} + void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) { struct netdev_adjacent *iter; + struct net *net = dev_net(dev); + list_for_each_entry(iter, &dev->adj_list.upper, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_add(iter->dev, dev, @@ -5032,6 +5136,8 @@ void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) } list_for_each_entry(iter, &dev->adj_list.lower, list) { + if (!net_eq(net,dev_net(iter->dev))) + continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_add(iter->dev, dev, @@ -5054,6 +5160,30 @@ void *netdev_lower_dev_get_private(struct net_device *dev, } EXPORT_SYMBOL(netdev_lower_dev_get_private); + +int dev_get_nest_level(struct net_device *dev, + bool (*type_check)(struct net_device *dev)) +{ + struct net_device *lower = NULL; + struct list_head *iter; + int max_nest = -1; + int nest; + + ASSERT_RTNL(); + + netdev_for_each_lower_dev(dev, lower, iter) { + nest = dev_get_nest_level(lower, type_check); + if (max_nest < nest) + max_nest = nest; + } + + if (type_check(dev)) + max_nest++; + + return max_nest; +} +EXPORT_SYMBOL(dev_get_nest_level); + static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; @@ -5523,7 +5653,7 @@ static int dev_new_index(struct net *net) /* Delayed registration/unregisteration */ static LIST_HEAD(net_todo_list); -static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); +DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); static void net_set_todo(struct net_device *dev) { @@ -5566,6 +5696,7 @@ static void rollback_registered_many(struct list_head *head) unlist_netdevice(dev); dev->reg_state = NETREG_UNREGISTERING; + on_each_cpu(flush_backlog, dev, 1); } synchronize_net(); @@ -5823,7 +5954,8 @@ static int netif_alloc_netdev_queues(struct net_device *dev) struct netdev_queue *tx; size_t sz = count * sizeof(*tx); - BUG_ON(count < 1 || count > 0xffff); + if (count < 1 || count > 0xffff) + return -EINVAL; tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); if (!tx) { @@ -6181,8 +6313,6 @@ void netdev_run_todo(void) dev->reg_state = NETREG_UNREGISTERED; - on_each_cpu(flush_backlog, dev, 1); - netdev_wait_allrefs(dev); /* paranoia */ @@ -6496,6 +6626,9 @@ EXPORT_SYMBOL(unregister_netdevice_queue); /** * unregister_netdevice_many - unregister many devices * @head: list of devices + * + * Note: As most callers use a stack allocated list_head, + * we force a list_del() to make sure stack wont be corrupted later. */ void unregister_netdevice_many(struct list_head *head) { @@ -6505,6 +6638,7 @@ void unregister_netdevice_many(struct list_head *head) rollback_registered_many(head); list_for_each_entry(dev, head, unreg_list) net_set_todo(dev); + list_del(head); } } EXPORT_SYMBOL(unregister_netdevice_many); @@ -6610,6 +6744,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Send a netdev-removed uevent to the old namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE); + netdev_adjacent_del_links(dev); /* Actually switch the network namespace */ dev_net_set(dev, net); @@ -6624,6 +6759,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Send a netdev-add uevent to the new namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_ADD); + netdev_adjacent_add_links(dev); /* Fixup kobjects */ err = device_rename(&dev->dev, dev->name); @@ -6680,10 +6816,20 @@ static int dev_cpu_callback(struct notifier_block *nfb, oldsd->output_queue = NULL; oldsd->output_queue_tailp = &oldsd->output_queue; } - /* Append NAPI poll list from offline CPU. */ - if (!list_empty(&oldsd->poll_list)) { - list_splice_init(&oldsd->poll_list, &sd->poll_list); - raise_softirq_irqoff(NET_RX_SOFTIRQ); + /* Append NAPI poll list from offline CPU, with one exception : + * process_backlog() must be called by cpu owning percpu backlog. + * We properly handle process_queue & input_pkt_queue later. + */ + while (!list_empty(&oldsd->poll_list)) { + struct napi_struct *napi = list_first_entry(&oldsd->poll_list, + struct napi_struct, + poll_list); + + list_del_init(&napi->poll_list); + if (napi->poll == process_backlog) + napi->state = 0; + else + ____napi_schedule(sd, napi); } raise_softirq_irqoff(NET_TX_SOFTIRQ); @@ -6694,7 +6840,7 @@ static int dev_cpu_callback(struct notifier_block *nfb, netif_rx_internal(skb); input_queue_head_incr(oldsd); } - while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { + while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx_internal(skb); input_queue_head_incr(oldsd); } @@ -6960,7 +7106,6 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) } } unregister_netdevice_many(&dev_kill_list); - list_del(&dev_kill_list); rtnl_unlock(); } diff --git a/net/core/dst.c b/net/core/dst.c index ca4231ec7347..c07070544e3f 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -267,6 +267,15 @@ again: } EXPORT_SYMBOL(dst_destroy); +static void dst_destroy_rcu(struct rcu_head *head) +{ + struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); + + dst = dst_destroy(dst); + if (dst) + __dst_free(dst); +} + void dst_release(struct dst_entry *dst) { if (dst) { @@ -274,11 +283,8 @@ void dst_release(struct dst_entry *dst) newrefcnt = atomic_dec_return(&dst->__refcnt); WARN_ON(newrefcnt < 0); - if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) { - dst = dst_destroy(dst); - if (dst) - __dst_free(dst); - } + if (!newrefcnt && unlikely(dst->flags & DST_NOCACHE)) + call_rcu(&dst->rcu_head, dst_destroy_rcu); } } EXPORT_SYMBOL(dst_release); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 30071dec287a..0b39ab6f7675 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1080,7 +1080,7 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) gstrings.len = ret; - data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); + data = kcalloc(gstrings.len, ETH_GSTRING_LEN, GFP_USER); if (!data) return -ENOMEM; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 5cbcdfd89f38..cfe1120d344e 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -670,15 +670,17 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, { int idx = 0; struct fib_rule *rule; + int err = 0; rcu_read_lock(); list_for_each_entry_rcu(rule, &ops->rules_list, list) { if (idx < cb->args[1]) goto skip; - if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, RTM_NEWRULE, - NLM_F_MULTI, ops) < 0) + err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWRULE, + NLM_F_MULTI, ops); + if (err < 0) break; skip: idx++; @@ -687,7 +689,7 @@ skip: cb->args[1] = idx; rules_ops_put(ops); - return skb->len; + return err; } static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) @@ -703,7 +705,9 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) if (ops == NULL) return -EAFNOSUPPORT; - return dump_rules(skb, cb, ops); + dump_rules(skb, cb, ops); + + return skb->len; } rcu_read_lock(); diff --git a/net/core/filter.c b/net/core/filter.c index ad30d626a5bd..ebce437678fc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -355,6 +355,8 @@ load_b: if (skb_is_nonlinear(skb)) return 0; + if (skb->len < sizeof(struct nlattr)) + return 0; if (A > skb->len - sizeof(struct nlattr)) return 0; @@ -371,11 +373,13 @@ load_b: if (skb_is_nonlinear(skb)) return 0; + if (skb->len < sizeof(struct nlattr)) + return 0; if (A > skb->len - sizeof(struct nlattr)) return 0; nla = (struct nlattr *)&skb->data[A]; - if (nla->nla_len > A - skb->len) + if (nla->nla_len > skb->len - A) return 0; nla = nla_find_nested(nla, X); diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 9d3d9e78397b..372ac662adf9 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -32,6 +32,9 @@ gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size) return 0; nla_put_failure: + kfree(d->xstats); + d->xstats = NULL; + d->xstats_len = 0; spin_unlock_bh(d->lock); return -1; } @@ -217,7 +220,9 @@ int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len) { if (d->compat_xstats) { - d->xstats = st; + d->xstats = kmemdup(st, len, GFP_ATOMIC); + if (!d->xstats) + goto err_out; d->xstats_len = len; } @@ -225,6 +230,11 @@ gnet_stats_copy_app(struct gnet_dump *d, void *st, int len) return gnet_stats_copy(d, TCA_STATS_APP, st, len); return 0; + +err_out: + d->xstats_len = 0; + spin_unlock_bh(d->lock); + return -1; } EXPORT_SYMBOL(gnet_stats_copy_app); @@ -257,6 +267,9 @@ gnet_stats_finish_copy(struct gnet_dump *d) return -1; } + kfree(d->xstats); + d->xstats = NULL; + d->xstats_len = 0; spin_unlock_bh(d->lock); return 0; } diff --git a/net/core/iovec.c b/net/core/iovec.c index b61869429f4c..26dc0062652f 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -39,7 +39,7 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a { int size, ct, err; - if (m->msg_namelen) { + if (m->msg_name && m->msg_namelen) { if (mode == VERIFY_READ) { void __user *namep; namep = (void __user __force *) m->msg_name; @@ -48,10 +48,10 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a if (err < 0) return err; } - if (m->msg_name) - m->msg_name = address; + m->msg_name = address; } else { m->msg_name = NULL; + m->msg_namelen = 0; } size = m->msg_iovlen * sizeof(struct iovec); @@ -107,6 +107,10 @@ EXPORT_SYMBOL(memcpy_toiovecend); int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, int offset, int len) { + /* No data? Done! */ + if (len == 0) + return 0; + /* Skip over the finished iovecs */ while (offset >= iov->iov_len) { offset -= iov->iov_len; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e16129019c66..0f062c671da9 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -976,6 +976,8 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) rc = 0; if (neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE)) goto out_unlock_bh; + if (neigh->dead) + goto out_dead; if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) { if (NEIGH_VAR(neigh->parms, MCAST_PROBES) + @@ -1032,6 +1034,13 @@ out_unlock_bh: write_unlock(&neigh->lock); local_bh_enable(); return rc; + +out_dead: + if (neigh->nud_state & NUD_STALE) + goto out_unlock_bh; + write_unlock_bh(&neigh->lock); + kfree_skb(skb); + return 1; } EXPORT_SYMBOL(__neigh_event_send); @@ -1095,6 +1104,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, if (!(flags & NEIGH_UPDATE_F_ADMIN) && (old & (NUD_NOARP | NUD_PERMANENT))) goto out; + if (neigh->dead) + goto out; if (!(new & NUD_VALID)) { neigh_del_timer(neigh); @@ -1244,11 +1255,13 @@ EXPORT_SYMBOL(neigh_update); */ void __neigh_set_probe_once(struct neighbour *neigh) { + if (neigh->dead) + return; 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->nud_state = NUD_INCOMPLETE; + atomic_set(&neigh->probes, neigh_max_probes(neigh)); neigh_add_timer(neigh, jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME)); } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 81d3a9a08453..7c8ffd974961 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -24,7 +24,7 @@ static LIST_HEAD(pernet_list); static struct list_head *first_device = &pernet_list; -static DEFINE_MUTEX(net_mutex); +DEFINE_MUTEX(net_mutex); LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index df9e6b1a9759..723fa7da8025 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -788,7 +788,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) } if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { - skb = vlan_untag(skb); + skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index fdac61cac1bd..dbd797a62b3a 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2812,25 +2812,25 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, skb->dev = odev; skb->pkt_type = PACKET_HOST; + pktgen_finalize_skb(pkt_dev, skb, datalen); + if (!(pkt_dev->flags & F_UDPCSUM)) { skb->ip_summed = CHECKSUM_NONE; } else if (odev->features & NETIF_F_V4_CSUM) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; - udp4_hwcsum(skb, udph->source, udph->dest); + udp4_hwcsum(skb, iph->saddr, iph->daddr); } else { - __wsum csum = udp_csum(skb); + __wsum csum = skb_checksum(skb, skb_transport_offset(skb), datalen + 8, 0); /* add protocol-dependent pseudo-header */ - udph->check = csum_tcpudp_magic(udph->source, udph->dest, + udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr, datalen + 8, IPPROTO_UDP, csum); if (udph->check == 0) udph->check = CSUM_MANGLED_0; } - pktgen_finalize_skb(pkt_dev, skb, datalen); - #ifdef CONFIG_XFRM if (!process_ipsec(pkt_dev, skb, protocol)) return NULL; @@ -2946,6 +2946,8 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, skb->dev = odev; skb->pkt_type = PACKET_HOST; + pktgen_finalize_skb(pkt_dev, skb, datalen); + if (!(pkt_dev->flags & F_UDPCSUM)) { skb->ip_summed = CHECKSUM_NONE; } else if (odev->features & NETIF_F_V6_CSUM) { @@ -2954,7 +2956,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, skb->csum_offset = offsetof(struct udphdr, check); udph->check = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, 0); } else { - __wsum csum = udp_csum(skb); + __wsum csum = skb_checksum(skb, skb_transport_offset(skb), udplen, 0); /* add protocol-dependent pseudo-header */ udph->check = csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, csum); @@ -2963,8 +2965,6 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, udph->check = CSUM_MANGLED_0; } - pktgen_finalize_skb(pkt_dev, skb, datalen); - return skb; } @@ -3464,8 +3464,10 @@ static int pktgen_thread_worker(void *arg) pktgen_rem_thread(t); /* Wait for kthread_stop */ - while (!kthread_should_stop()) { + for (;;) { set_current_state(TASK_INTERRUPTIBLE); + if (kthread_should_stop()) + break; schedule(); } __set_current_state(TASK_RUNNING); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 120eecc0f5a4..465092f8fb76 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -353,15 +353,46 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops) } EXPORT_SYMBOL_GPL(__rtnl_link_unregister); +/* Return with the rtnl_lock held when there are no network + * devices unregistering in any network namespace. + */ +static void rtnl_lock_unregistering_all(void) +{ + struct net *net; + bool unregistering; + DEFINE_WAIT(wait); + + for (;;) { + prepare_to_wait(&netdev_unregistering_wq, &wait, + TASK_UNINTERRUPTIBLE); + unregistering = false; + rtnl_lock(); + for_each_net(net) { + if (net->dev_unreg_count > 0) { + unregistering = true; + break; + } + } + if (!unregistering) + break; + __rtnl_unlock(); + schedule(); + } + finish_wait(&netdev_unregistering_wq, &wait); +} + /** * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink. * @ops: struct rtnl_link_ops * to unregister */ void rtnl_link_unregister(struct rtnl_link_ops *ops) { - rtnl_lock(); + /* Close the race with cleanup_net() */ + mutex_lock(&net_mutex); + rtnl_lock_unregistering_all(); __rtnl_link_unregister(ops); rtnl_unlock(); + mutex_unlock(&net_mutex); } EXPORT_SYMBOL_GPL(rtnl_link_unregister); @@ -768,13 +799,15 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, (nla_total_size(sizeof(struct ifla_vf_mac)) + nla_total_size(sizeof(struct ifla_vf_vlan)) + nla_total_size(sizeof(struct ifla_vf_tx_rate)) + - nla_total_size(sizeof(struct ifla_vf_spoofchk))); + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + + nla_total_size(sizeof(struct ifla_vf_link_state))); return size; } else return 0; } -static size_t rtnl_port_size(const struct net_device *dev) +static size_t rtnl_port_size(const struct net_device *dev, + u32 ext_filter_mask) { size_t port_size = nla_total_size(4) /* PORT_VF */ + nla_total_size(PORT_PROFILE_MAX) /* PORT_PROFILE */ @@ -790,7 +823,8 @@ static size_t rtnl_port_size(const struct net_device *dev) size_t port_self_size = nla_total_size(sizeof(struct nlattr)) + port_size; - if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) return 0; if (dev_num_vf(dev->dev.parent)) return port_self_size + vf_ports_size + @@ -825,7 +859,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(ext_filter_mask & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */ + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ - + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */ @@ -887,11 +921,13 @@ static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev) return 0; } -static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) +static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev, + u32 ext_filter_mask) { int err; - if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) return 0; err = rtnl_port_self_fill(skb, dev); @@ -1076,7 +1112,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_nest_end(skb, vfinfo); } - if (rtnl_port_fill(skb, dev)) + if (rtnl_port_fill(skb, dev, ext_filter_mask)) goto nla_put_failure; if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) { @@ -1130,6 +1166,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) struct hlist_head *head; struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; + int err; + int hdrlen; s_h = cb->args[0]; s_idx = cb->args[1]; @@ -1137,8 +1175,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); cb->seq = net->dev_base_seq; - if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, - ifla_policy) >= 0) { + /* A hack to preserve kernel<->userspace interface. + * The correct header is ifinfomsg. It is consistent with rtnl_getlink. + * However, before Linux v3.9 the code here assumed rtgenmsg and that's + * what iproute2 < v3.9.0 used. + * We can detect the old iproute2. Even including the IFLA_EXT_MASK + * attribute, its netlink message is shorter than struct ifinfomsg. + */ + hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ? + sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg); + + if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) { if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); @@ -1150,11 +1197,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; - if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI, - ext_filter_mask) <= 0) + err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, 0, + NLM_F_MULTI, + ext_filter_mask); + /* If we ran out of room on the first message, + * we're in trouble + */ + WARN_ON((err == -EMSGSIZE) && (skb->len == 0)); + + if (err <= 0) goto out; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -1206,19 +1259,11 @@ static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { [IFLA_INFO_SLAVE_DATA] = { .type = NLA_NESTED }, }; -static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = { - [IFLA_VF_INFO] = { .type = NLA_NESTED }, -}; - static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { - [IFLA_VF_MAC] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_mac) }, - [IFLA_VF_VLAN] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_vlan) }, - [IFLA_VF_TX_RATE] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_tx_rate) }, - [IFLA_VF_SPOOFCHK] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_spoofchk) }, + [IFLA_VF_MAC] = { .len = sizeof(struct ifla_vf_mac) }, + [IFLA_VF_VLAN] = { .len = sizeof(struct ifla_vf_vlan) }, + [IFLA_VF_TX_RATE] = { .len = sizeof(struct ifla_vf_tx_rate) }, + [IFLA_VF_SPOOFCHK] = { .len = sizeof(struct ifla_vf_spoofchk) }, }; static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { @@ -1287,67 +1332,66 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) return 0; } -static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) +static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) { - int rem, err = -EINVAL; - struct nlattr *vf; const struct net_device_ops *ops = dev->netdev_ops; + int err = -EINVAL; - nla_for_each_nested(vf, attr, rem) { - switch (nla_type(vf)) { - case IFLA_VF_MAC: { - struct ifla_vf_mac *ivm; - ivm = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_mac) - err = ops->ndo_set_vf_mac(dev, ivm->vf, - ivm->mac); - break; - } - case IFLA_VF_VLAN: { - struct ifla_vf_vlan *ivv; - ivv = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_vlan) - err = ops->ndo_set_vf_vlan(dev, ivv->vf, - ivv->vlan, - ivv->qos); - break; - } - case IFLA_VF_TX_RATE: { - struct ifla_vf_tx_rate *ivt; - ivt = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_tx_rate) - err = ops->ndo_set_vf_tx_rate(dev, ivt->vf, - ivt->rate); - break; - } - case IFLA_VF_SPOOFCHK: { - struct ifla_vf_spoofchk *ivs; - ivs = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_spoofchk) - err = ops->ndo_set_vf_spoofchk(dev, ivs->vf, - ivs->setting); - break; - } - case IFLA_VF_LINK_STATE: { - struct ifla_vf_link_state *ivl; - ivl = nla_data(vf); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_link_state) - err = ops->ndo_set_vf_link_state(dev, ivl->vf, - ivl->link_state); - break; - } - default: - err = -EINVAL; - break; - } - if (err) - break; + if (tb[IFLA_VF_MAC]) { + struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]); + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_mac) + err = ops->ndo_set_vf_mac(dev, ivm->vf, + ivm->mac); + if (err < 0) + return err; + } + + if (tb[IFLA_VF_VLAN]) { + struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]); + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_vlan) + err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan, + ivv->qos); + if (err < 0) + return err; + } + + if (tb[IFLA_VF_TX_RATE]) { + struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]); + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_tx_rate) + err = ops->ndo_set_vf_tx_rate(dev, ivt->vf, + ivt->rate); + if (err < 0) + return err; + } + + if (tb[IFLA_VF_SPOOFCHK]) { + struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]); + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_spoofchk) + err = ops->ndo_set_vf_spoofchk(dev, ivs->vf, + ivs->setting); + if (err < 0) + return err; + } + + if (tb[IFLA_VF_LINK_STATE]) { + struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]); + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_link_state) + err = ops->ndo_set_vf_link_state(dev, ivl->vf, + ivl->link_state); + if (err < 0) + return err; } + return err; } @@ -1386,7 +1430,8 @@ static int do_set_master(struct net_device *dev, int ifindex) return 0; } -static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, +static int do_setlink(const struct sk_buff *skb, + struct net_device *dev, struct ifinfomsg *ifm, struct nlattr **tb, char *ifname, int modified) { const struct net_device_ops *ops = dev->netdev_ops; @@ -1398,7 +1443,8 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, err = PTR_ERR(net); goto errout; } - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + put_net(net); err = -EPERM; goto errout; } @@ -1528,14 +1574,21 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, } if (tb[IFLA_VFINFO_LIST]) { + struct nlattr *vfinfo[IFLA_VF_MAX + 1]; struct nlattr *attr; int rem; + nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) { - if (nla_type(attr) != IFLA_VF_INFO) { + if (nla_type(attr) != IFLA_VF_INFO || + nla_len(attr) < NLA_HDRLEN) { err = -EINVAL; goto errout; } - err = do_setvfinfo(dev, attr); + err = nla_parse_nested(vfinfo, IFLA_VF_MAX, attr, + ifla_vf_policy); + if (err < 0) + goto errout; + err = do_setvfinfo(dev, vfinfo); if (err < 0) goto errout; modified = 1; @@ -1652,7 +1705,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) if (err < 0) goto errout; - err = do_setlink(dev, ifm, tb, ifname, 0); + err = do_setlink(skb, dev, ifm, tb, ifname, 0); errout: return err; } @@ -1692,7 +1745,6 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) ops->dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); - list_del(&list_kill); return 0; } @@ -1769,7 +1821,8 @@ err: } EXPORT_SYMBOL(rtnl_create_link); -static int rtnl_group_changelink(struct net *net, int group, +static int rtnl_group_changelink(const struct sk_buff *skb, + struct net *net, int group, struct ifinfomsg *ifm, struct nlattr **tb) { @@ -1778,7 +1831,7 @@ static int rtnl_group_changelink(struct net *net, int group, for_each_netdev(net, dev) { if (dev->group == group) { - err = do_setlink(dev, ifm, tb, NULL, 0); + err = do_setlink(skb, dev, ifm, tb, NULL, 0); if (err < 0) return err; } @@ -1920,12 +1973,12 @@ replay: modified = 1; } - return do_setlink(dev, ifm, tb, ifname, modified); + return do_setlink(skb, dev, ifm, tb, ifname, modified); } if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { if (ifm->ifi_index == 0 && tb[IFLA_GROUP]) - return rtnl_group_changelink(net, + return rtnl_group_changelink(skb, net, nla_get_u32(tb[IFLA_GROUP]), ifm, tb); return -ENODEV; @@ -1979,8 +2032,16 @@ replay: } } err = rtnl_configure_link(dev, ifm); - if (err < 0) - unregister_netdevice(dev); + if (err < 0) { + if (ops->newlink) { + LIST_HEAD(list_kill); + + ops->dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + } else { + unregister_netdevice(dev); + } + } out: put_net(dest_net); return err; @@ -2042,9 +2103,13 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; u16 min_ifinfo_dump_size = 0; + int hdrlen; - if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, - ifla_policy) >= 0) { + /* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */ + hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ? + sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg); + + if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) { if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); } @@ -2312,7 +2377,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) int err = -EINVAL; __u8 *addr; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); @@ -2590,12 +2655,16 @@ static int rtnl_bridge_notify(struct net_device *dev, u16 flags) goto errout; } + if (!skb->len) + goto errout; + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return 0; errout: WARN_ON(err == -EMSGSIZE); kfree_skb(skb); - rtnl_set_sk_err(net, RTNLGRP_LINK, err); + if (err) + rtnl_set_sk_err(net, RTNLGRP_LINK, err); return err; } @@ -2764,7 +2833,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) sz_idx = type>>2; kind = type&3; - if (kind != 2 && !ns_capable(net->user_ns, CAP_NET_ADMIN)) + if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 897da56f3aff..ba71212f0251 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -85,31 +85,6 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET -__u32 secure_ip_id(__be32 daddr) -{ - u32 hash[MD5_DIGEST_WORDS]; - - net_secret_init(); - hash[0] = (__force __u32) daddr; - hash[1] = net_secret[13]; - hash[2] = net_secret[14]; - hash[3] = net_secret[15]; - - md5_transform(hash, net_secret); - - return hash[0]; -} - -__u32 secure_ipv6_id(const __be32 daddr[4]) -{ - __u32 hash[4]; - - net_secret_init(); - memcpy(hash, daddr, 16); - md5_transform(hash, net_secret); - - return hash[0]; -} __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 90b96a11b974..366f7ff741b7 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -62,6 +62,7 @@ #include <linux/scatterlist.h> #include <linux/errqueue.h> #include <linux/prefetch.h> +#include <linux/if_vlan.h> #include <net/protocol.h> #include <net/dst.h> @@ -277,13 +278,14 @@ nodata: EXPORT_SYMBOL(__alloc_skb); /** - * build_skb - build a network buffer + * __build_skb - build a network buffer * @data: data buffer provided by caller - * @frag_size: size of fragment, or 0 if head was kmalloced + * @frag_size: size of data, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated by kmalloc() only if - * @frag_size is 0, otherwise data should come from the page allocator. + * @frag_size is 0, otherwise data should come from the page allocator + * or vmalloc() * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : @@ -294,7 +296,7 @@ EXPORT_SYMBOL(__alloc_skb); * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ -struct sk_buff *build_skb(void *data, unsigned int frag_size) +struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct skb_shared_info *shinfo; struct sk_buff *skb; @@ -308,7 +310,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) memset(skb, 0, offsetof(struct sk_buff, tail)); skb->truesize = SKB_TRUESIZE(size); - skb->head_frag = frag_size != 0; atomic_set(&skb->users, 1); skb->head = data; skb->data = data; @@ -325,6 +326,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) return skb; } + +/* build_skb() is wrapper over __build_skb(), that specifically + * takes care of skb->head and skb->pfmemalloc + * This means that if @frag_size is not zero, then @data must be backed + * by a page fragment, not kmalloc() or vmalloc() + */ +struct sk_buff *build_skb(void *data, unsigned int frag_size) +{ + struct sk_buff *skb = __build_skb(data, frag_size); + + if (skb && frag_size) { + skb->head_frag = 1; + if (virt_to_head_page(data)->pfmemalloc) + skb->pfmemalloc = 1; + } + return skb; +} EXPORT_SYMBOL(build_skb); struct netdev_alloc_cache { @@ -350,8 +368,11 @@ refill: for (order = NETDEV_FRAG_PAGE_MAX_ORDER; ;) { gfp_t gfp = gfp_mask; - if (order) - gfp |= __GFP_COMP | __GFP_NOWARN; + if (order) { + gfp |= __GFP_COMP | __GFP_NOWARN | + __GFP_NOMEMALLOC; + gfp &= ~__GFP_WAIT; + } nc->frag.page = alloc_pages(gfp, order); if (likely(nc->frag.page)) break; @@ -2841,11 +2862,12 @@ EXPORT_SYMBOL(skb_append_datato_frags); */ unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) { + unsigned char *data = skb->data; + BUG_ON(len > skb->len); - skb->len -= len; - BUG_ON(skb->len < skb->data_len); - skb_postpull_rcsum(skb, skb->data, len); - return skb->data += len; + __skb_pull(skb, len); + skb_postpull_rcsum(skb, data, len); + return skb->data; } EXPORT_SYMBOL_GPL(skb_pull_rcsum); @@ -2881,12 +2903,13 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, int pos; int dummy; + __skb_push(head_skb, doffset); proto = skb_network_protocol(head_skb, &dummy); if (unlikely(!proto)) return ERR_PTR(-EINVAL); csum = !!can_checksum_protocol(features, proto); - __skb_push(head_skb, doffset); + headroom = skb_headroom(head_skb); pos = skb_headlen(head_skb); @@ -2967,9 +2990,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, tail = nskb; __copy_skb_header(nskb, head_skb); - nskb->mac_len = head_skb->mac_len; skb_headers_offset_update(nskb, skb_headroom(nskb) - headroom); + skb_reset_mac_len(nskb); skb_copy_from_linear_data_offset(head_skb, -tnl_hlen, nskb->data - tnl_hlen, @@ -3076,7 +3099,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) if (unlikely(p->len + len >= 65536)) return -E2BIG; - lp = NAPI_GRO_CB(p)->last ?: p; + lp = NAPI_GRO_CB(p)->last; pinfo = skb_shinfo(lp); if (headlen <= offset) { @@ -3138,6 +3161,9 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; goto done; } + /* switch back to head shinfo */ + pinfo = skb_shinfo(p); + if (pinfo->frag_list) goto merge; if (skb_gro_len(p) != pinfo->gso_size) @@ -3192,7 +3218,7 @@ merge: __skb_pull(skb, offset); - if (!NAPI_GRO_CB(p)->last) + if (NAPI_GRO_CB(p)->last == p) skb_shinfo(p)->frag_list = skb; else NAPI_GRO_CB(p)->last->next = skb; @@ -3932,6 +3958,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->local_df = 0; skb_dst_drop(skb); skb->mark = 0; + skb_init_secmark(skb); secpath_reset(skb); nf_reset(skb); nf_reset_trace(skb); @@ -3951,12 +3978,66 @@ EXPORT_SYMBOL_GPL(skb_scrub_packet); unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); - unsigned int hdr_len; if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) - hdr_len = tcp_hdrlen(skb); - else - hdr_len = sizeof(struct udphdr); - return hdr_len + shinfo->gso_size; + return tcp_hdrlen(skb) + shinfo->gso_size; + + /* UFO sets gso_size to the size of the fragmentation + * payload, i.e. the size of the L4 (UDP) header is already + * accounted for. + */ + return shinfo->gso_size; } EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); + +static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) +{ + if (skb_cow(skb, skb_headroom(skb)) < 0) { + kfree_skb(skb); + return NULL; + } + + memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN); + skb->mac_header += VLAN_HLEN; + return skb; +} + +struct sk_buff *skb_vlan_untag(struct sk_buff *skb) +{ + struct vlan_hdr *vhdr; + u16 vlan_tci; + + if (unlikely(vlan_tx_tag_present(skb))) { + /* vlan_tci is already set-up so leave this for another time */ + return skb; + } + + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) + goto err_free; + + if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) + goto err_free; + + vhdr = (struct vlan_hdr *)skb->data; + vlan_tci = ntohs(vhdr->h_vlan_TCI); + __vlan_hwaccel_put_tag(skb, skb->protocol, vlan_tci); + + skb_pull_rcsum(skb, VLAN_HLEN); + vlan_set_encap_proto(skb, vhdr); + + skb = skb_reorder_vlan_header(skb); + if (unlikely(!skb)) + goto err_free; + + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + skb_reset_mac_len(skb); + + return skb; + +err_free: + kfree_skb(skb); + return NULL; +} +EXPORT_SYMBOL(skb_vlan_untag); diff --git a/net/core/sock.c b/net/core/sock.c index c0fc6bdad1e3..8ebfa52e5d70 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -145,6 +145,55 @@ static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); +/** + * sk_ns_capable - General socket capability test + * @sk: Socket to use a capability on or through + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in the user + * namespace @user_ns. + */ +bool sk_ns_capable(const struct sock *sk, + struct user_namespace *user_ns, int cap) +{ + return file_ns_capable(sk->sk_socket->file, user_ns, cap) && + ns_capable(user_ns, cap); +} +EXPORT_SYMBOL(sk_ns_capable); + +/** + * sk_capable - Socket global capability test + * @sk: Socket to use a capability on or through + * @cap: The global capbility to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in all user + * namespaces. + */ +bool sk_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, &init_user_ns, cap); +} +EXPORT_SYMBOL(sk_capable); + +/** + * sk_net_capable - Network namespace socket capability test + * @sk: Socket to use a capability on or through + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socke was created + * and the current process has the capability @cap over the network namespace + * the socket is a member of. + */ +bool sk_net_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); +} +EXPORT_SYMBOL(sk_net_capable); + + #ifdef CONFIG_MEMCG_KMEM int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { @@ -610,6 +659,25 @@ static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool) sock_reset_flag(sk, bit); } +bool sk_mc_loop(struct sock *sk) +{ + if (dev_recursion_level()) + return false; + if (!sk) + return true; + switch (sk->sk_family) { + case AF_INET: + return inet_sk(sk)->mc_loop; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + return inet6_sk(sk)->mc_loop; +#endif + } + WARN_ON(1); + return true; +} +EXPORT_SYMBOL(sk_mc_loop); + /* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic. @@ -1846,8 +1914,10 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio) do { gfp_t gfp = prio; - if (order) + if (order) { gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY; + gfp &= ~__GFP_WAIT; + } pfrag->page = alloc_pages(gfp, order); if (likely(pfrag->page)) { pfrag->offset = 0; diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index a0e9cf6379de..c38e7a2b5a8e 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -49,7 +49,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) } EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); -int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, +int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype) { struct nlattr *attr; @@ -57,7 +57,7 @@ int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, unsigned int len; int err = 0; - if (!ns_capable(user_ns, CAP_NET_ADMIN)) { + if (!may_report_filterinfo) { nla_reserve(skb, attrtype, 0); return 0; } diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index cf9cd13509a7..e731c96eac4b 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -25,6 +25,8 @@ static int zero = 0; static int one = 1; static int ushort_max = USHRT_MAX; +static int min_sndbuf = SOCK_MIN_SNDBUF; +static int min_rcvbuf = SOCK_MIN_RCVBUF; #ifdef CONFIG_RPS static int rps_sock_flow_sysctl(struct ctl_table *table, int write, @@ -223,7 +225,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_sndbuf, }, { .procname = "rmem_max", @@ -231,7 +233,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_rcvbuf, }, { .procname = "wmem_default", @@ -239,7 +241,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_sndbuf, }, { .procname = "rmem_default", @@ -247,7 +249,7 @@ static struct ctl_table net_core_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &one, + .extra1 = &min_rcvbuf, }, { .procname = "dev_weight", diff --git a/net/core/utils.c b/net/core/utils.c index 2f737bf90b3f..eed34338736c 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -348,8 +348,8 @@ static void __net_random_once_deferred(struct work_struct *w) { struct __net_random_once_work *work = container_of(w, struct __net_random_once_work, work); - if (!static_key_enabled(work->key)) - static_key_slow_inc(work->key); + BUG_ON(!static_key_enabled(work->key)); + static_key_slow_dec(work->key); kfree(work); } @@ -367,7 +367,7 @@ static void __net_random_once_disable_jump(struct static_key *key) } bool __net_get_random_once(void *buf, int nbytes, bool *done, - struct static_key *done_key) + struct static_key *once_key) { static DEFINE_SPINLOCK(lock); unsigned long flags; @@ -382,7 +382,7 @@ bool __net_get_random_once(void *buf, int nbytes, bool *done, *done = true; spin_unlock_irqrestore(&lock, flags); - __net_random_once_disable_jump(done_key); + __net_random_once_disable_jump(once_key); return true; } |