diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/dev.c | 87 | ||||
-rw-r--r-- | net/core/drop_monitor.c | 113 | ||||
-rw-r--r-- | net/core/ethtool.c | 1 | ||||
-rw-r--r-- | net/core/neighbour.c | 6 | ||||
-rw-r--r-- | net/core/net_namespace.c | 4 | ||||
-rw-r--r-- | net/core/netpoll.c | 11 | ||||
-rw-r--r-- | net/core/pktgen.c | 12 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 9 | ||||
-rw-r--r-- | net/core/sock.c | 11 |
9 files changed, 143 insertions, 111 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index f134f88..5b84eaf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1045,6 +1045,8 @@ rollback: */ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) { + char *new_ifalias; + ASSERT_RTNL(); if (len >= IFALIASZ) @@ -1058,9 +1060,10 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) return 0; } - dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); - if (!dev->ifalias) + new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); + if (!new_ifalias) return -ENOMEM; + dev->ifalias = new_ifalias; strlcpy(dev->ifalias, alias, len+1); return len; @@ -1163,6 +1166,7 @@ static int __dev_open(struct net_device *dev) net_dmaengine_get(); dev_set_rx_mode(dev); dev_activate(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); } return ret; @@ -1406,14 +1410,34 @@ EXPORT_SYMBOL(register_netdevice_notifier); * register_netdevice_notifier(). The notifier is unlinked into the * kernel structures and may then be reused. A negative errno code * is returned on a failure. + * + * After unregistering unregister and down device events are synthesized + * for all devices on the device list to the removed notifier to remove + * the need for special case cleanup code. */ int unregister_netdevice_notifier(struct notifier_block *nb) { + struct net_device *dev; + struct net *net; int err; rtnl_lock(); err = raw_notifier_chain_unregister(&netdev_chain, nb); + if (err) + goto unlock; + + for_each_net(net) { + for_each_netdev(net, dev) { + if (dev->flags & IFF_UP) { + nb->notifier_call(nb, NETDEV_GOING_DOWN, dev); + nb->notifier_call(nb, NETDEV_DOWN, dev); + } + nb->notifier_call(nb, NETDEV_UNREGISTER, dev); + nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev); + } + } +unlock: rtnl_unlock(); return err; } @@ -1513,10 +1537,14 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) kfree_skb(skb); return NET_RX_DROP; } - skb_set_dev(skb, dev); + skb->dev = dev; + skb_dst_drop(skb); skb->tstamp.tv64 = 0; skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, dev); + skb->mark = 0; + secpath_reset(skb); + nf_reset(skb); return netif_rx(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); @@ -1771,36 +1799,6 @@ void netif_device_attach(struct net_device *dev) } EXPORT_SYMBOL(netif_device_attach); -/** - * skb_dev_set -- assign a new device to a buffer - * @skb: buffer for the new device - * @dev: network device - * - * If an skb is owned by a device already, we have to reset - * all data private to the namespace a device belongs to - * before assigning it a new device. - */ -#ifdef CONFIG_NET_NS -void skb_set_dev(struct sk_buff *skb, struct net_device *dev) -{ - skb_dst_drop(skb); - if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) { - secpath_reset(skb); - nf_reset(skb); - skb_init_secmark(skb); - skb->mark = 0; - skb->priority = 0; - skb->nf_trace = 0; - skb->ipvs_property = 0; -#ifdef CONFIG_NET_SCHED - skb->tc_index = 0; -#endif - } - skb->dev = dev; -} -EXPORT_SYMBOL(skb_set_dev); -#endif /* CONFIG_NET_NS */ - /* * Invalidate hardware checksum when packet is to be mangled, and * complete checksum manually on outgoing path. @@ -2040,7 +2038,8 @@ static bool can_checksum_protocol(unsigned long features, __be16 protocol) static u32 harmonize_features(struct sk_buff *skb, __be16 protocol, u32 features) { - if (!can_checksum_protocol(features, protocol)) { + if (skb->ip_summed != CHECKSUM_NONE && + !can_checksum_protocol(features, protocol)) { features &= ~NETIF_F_ALL_CSUM; features &= ~NETIF_F_SG; } else if (illegal_highdma(skb->dev, skb)) { @@ -2055,6 +2054,9 @@ u32 netif_skb_features(struct sk_buff *skb) __be16 protocol = skb->protocol; u32 features = skb->dev->features; + if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) + features &= ~NETIF_F_GSO_MASK; + if (protocol == htons(ETH_P_8021Q)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; @@ -2558,16 +2560,17 @@ __u32 __skb_get_rxhash(struct sk_buff *skb) poff = proto_ports_offset(ip_proto); if (poff >= 0) { nhoff += ihl * 4 + poff; - if (pskb_may_pull(skb, nhoff + 4)) { + if (pskb_may_pull(skb, nhoff + 4)) ports.v32 = * (__force u32 *) (skb->data + nhoff); - if (ports.v16[1] < ports.v16[0]) - swap(ports.v16[0], ports.v16[1]); - } } /* get a consistent hash (same value on both flow directions) */ - if (addr2 < addr1) + if (addr2 < addr1 || + (addr2 == addr1 && + ports.v16[1] < ports.v16[0])) { swap(addr1, addr2); + swap(ports.v16[0], ports.v16[1]); + } hash = jhash_3words(addr1, addr2, ports.v32, hashrnd); if (!hash) @@ -4736,6 +4739,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) err = ops->ndo_set_mac_address(dev, sa); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + add_device_randomness(dev->dev_addr, dev->addr_len); return err; } EXPORT_SYMBOL(dev_set_mac_address); @@ -5513,6 +5517,7 @@ int register_netdevice(struct net_device *dev) dev_init_scheduler(dev); dev_hold(dev); list_netdevice(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); /* Notify protocols, that a new device appeared. */ ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); @@ -5873,6 +5878,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); dev->gso_max_size = GSO_MAX_SIZE; + dev->gso_max_segs = GSO_MAX_SEGS; INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list); dev->ethtool_ntuple_list.count = 0; @@ -6256,7 +6262,8 @@ static struct hlist_head *netdev_create_hash(void) /* Initialize per network namespace state */ static int __net_init netdev_init(struct net *net) { - INIT_LIST_HEAD(&net->dev_base_head); + if (net != &init_net) + INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 7f36b38..b856f87 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -33,22 +33,19 @@ #define TRACE_ON 1 #define TRACE_OFF 0 -static void send_dm_alert(struct work_struct *unused); - - /* * Globals, our netlink socket pointer * and the work handle that will send up * netlink alerts */ static int trace_state = TRACE_OFF; -static DEFINE_SPINLOCK(trace_state_lock); +static DEFINE_MUTEX(trace_state_mutex); struct per_cpu_dm_data { - struct work_struct dm_alert_work; - struct sk_buff *skb; - atomic_t dm_hit_count; - struct timer_list send_timer; + spinlock_t lock; + struct sk_buff *skb; + struct work_struct dm_alert_work; + struct timer_list send_timer; }; struct dm_hw_stat_delta { @@ -74,56 +71,59 @@ static int dm_delay = 1; static unsigned long dm_hw_check_delta = 2*HZ; static LIST_HEAD(hw_stats_list); -static void reset_per_cpu_data(struct per_cpu_dm_data *data) +static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) { size_t al; struct net_dm_alert_msg *msg; struct nlattr *nla; + struct sk_buff *skb; + unsigned long flags; al = sizeof(struct net_dm_alert_msg); al += dm_hit_limit * sizeof(struct net_dm_drop_point); al += sizeof(struct nlattr); - data->skb = genlmsg_new(al, GFP_KERNEL); - genlmsg_put(data->skb, 0, 0, &net_drop_monitor_family, - 0, NET_DM_CMD_ALERT); - nla = nla_reserve(data->skb, NLA_UNSPEC, sizeof(struct net_dm_alert_msg)); - msg = nla_data(nla); - memset(msg, 0, al); - atomic_set(&data->dm_hit_count, dm_hit_limit); + skb = genlmsg_new(al, GFP_KERNEL); + + if (skb) { + genlmsg_put(skb, 0, 0, &net_drop_monitor_family, + 0, NET_DM_CMD_ALERT); + nla = nla_reserve(skb, NLA_UNSPEC, + sizeof(struct net_dm_alert_msg)); + msg = nla_data(nla); + memset(msg, 0, al); + } else { + mod_timer(&data->send_timer, jiffies + HZ / 10); + } + + spin_lock_irqsave(&data->lock, flags); + swap(data->skb, skb); + spin_unlock_irqrestore(&data->lock, flags); + + return skb; } -static void send_dm_alert(struct work_struct *unused) +static void send_dm_alert(struct work_struct *work) { struct sk_buff *skb; - struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); + struct per_cpu_dm_data *data; - /* - * Grab the skb we're about to send - */ - skb = data->skb; + data = container_of(work, struct per_cpu_dm_data, dm_alert_work); - /* - * Replace it with a new one - */ - reset_per_cpu_data(data); - - /* - * Ship it! - */ - genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL); + skb = reset_per_cpu_data(data); + if (skb) + genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL); } /* * This is the timer function to delay the sending of an alert * in the event that more drops will arrive during the - * hysteresis period. Note that it operates under the timer interrupt - * so we don't need to disable preemption here + * hysteresis period. */ -static void sched_send_work(unsigned long unused) +static void sched_send_work(unsigned long _data) { - struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); + struct per_cpu_dm_data *data = (struct per_cpu_dm_data *)_data; schedule_work(&data->dm_alert_work); } @@ -134,17 +134,19 @@ static void trace_drop_common(struct sk_buff *skb, void *location) struct nlmsghdr *nlh; struct nlattr *nla; int i; - struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); + struct sk_buff *dskb; + struct per_cpu_dm_data *data; + unsigned long flags; + local_irq_save(flags); + data = &__get_cpu_var(dm_cpu_data); + spin_lock(&data->lock); + dskb = data->skb; - if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) { - /* - * we're already at zero, discard this hit - */ + if (!dskb) goto out; - } - nlh = (struct nlmsghdr *)data->skb->data; + nlh = (struct nlmsghdr *)dskb->data; nla = genlmsg_data(nlmsg_data(nlh)); msg = nla_data(nla); for (i = 0; i < msg->entries; i++) { @@ -153,11 +155,12 @@ static void trace_drop_common(struct sk_buff *skb, void *location) goto out; } } - + if (msg->entries == dm_hit_limit) + goto out; /* * We need to create a new entry */ - __nla_reserve_nohdr(data->skb, sizeof(struct net_dm_drop_point)); + __nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point)); nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point)); memcpy(msg->points[msg->entries].pc, &location, sizeof(void *)); msg->points[msg->entries].count = 1; @@ -165,11 +168,11 @@ static void trace_drop_common(struct sk_buff *skb, void *location) if (!timer_pending(&data->send_timer)) { data->send_timer.expires = jiffies + dm_delay * HZ; - add_timer_on(&data->send_timer, smp_processor_id()); + add_timer(&data->send_timer); } out: - return; + spin_unlock_irqrestore(&data->lock, flags); } static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location) @@ -213,7 +216,7 @@ static int set_all_monitor_traces(int state) struct dm_hw_stat_delta *new_stat = NULL; struct dm_hw_stat_delta *temp; - spin_lock(&trace_state_lock); + mutex_lock(&trace_state_mutex); if (state == trace_state) { rc = -EAGAIN; @@ -252,7 +255,7 @@ static int set_all_monitor_traces(int state) rc = -EINPROGRESS; out_unlock: - spin_unlock(&trace_state_lock); + mutex_unlock(&trace_state_mutex); return rc; } @@ -295,12 +298,12 @@ static int dropmon_net_event(struct notifier_block *ev_block, new_stat->dev = dev; new_stat->last_rx = jiffies; - spin_lock(&trace_state_lock); + mutex_lock(&trace_state_mutex); list_add_rcu(&new_stat->list, &hw_stats_list); - spin_unlock(&trace_state_lock); + mutex_unlock(&trace_state_mutex); break; case NETDEV_UNREGISTER: - spin_lock(&trace_state_lock); + mutex_lock(&trace_state_mutex); list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) { if (new_stat->dev == dev) { new_stat->dev = NULL; @@ -311,7 +314,7 @@ static int dropmon_net_event(struct notifier_block *ev_block, } } } - spin_unlock(&trace_state_lock); + mutex_unlock(&trace_state_mutex); break; } out: @@ -367,13 +370,15 @@ static int __init init_net_drop_monitor(void) for_each_present_cpu(cpu) { data = &per_cpu(dm_cpu_data, cpu); - reset_per_cpu_data(data); INIT_WORK(&data->dm_alert_work, send_dm_alert); init_timer(&data->send_timer); - data->send_timer.data = cpu; + data->send_timer.data = (unsigned long)data; data->send_timer.function = sched_send_work; + spin_lock_init(&data->lock); + reset_per_cpu_data(data); } + goto out; out_unreg: diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 4fb7704..891b19f 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1964,6 +1964,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GRXCSUM: case ETHTOOL_GTXCSUM: case ETHTOOL_GSG: + case ETHTOOL_GSSET_INFO: case ETHTOOL_GSTRINGS: case ETHTOOL_GTSO: case ETHTOOL_GPERMADDR: diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 96bb0a3..eb8857a 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1313,8 +1313,6 @@ int neigh_resolve_output(struct sk_buff *skb) if (!dst) goto discard; - __skb_pull(skb, skb_network_offset(skb)); - if (!neigh_event_send(neigh, skb)) { int err; struct net_device *dev = neigh->dev; @@ -1326,6 +1324,7 @@ int neigh_resolve_output(struct sk_buff *skb) neigh_hh_init(neigh, dst, dst->ops->protocol); do { + __skb_pull(skb, skb_network_offset(skb)); seq = read_seqbegin(&neigh->ha_lock); err = dev_hard_header(skb, dev, ntohs(skb->protocol), neigh->ha, NULL, skb->len); @@ -1358,9 +1357,8 @@ int neigh_connected_output(struct sk_buff *skb) struct net_device *dev = neigh->dev; unsigned int seq; - __skb_pull(skb, skb_network_offset(skb)); - do { + __skb_pull(skb, skb_network_offset(skb)); seq = read_seqbegin(&neigh->ha_lock); err = dev_hard_header(skb, dev, ntohs(skb->protocol), neigh->ha, NULL, skb->len); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 2772ed1..1642c30 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -24,7 +24,9 @@ static DEFINE_MUTEX(net_mutex); LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); -struct net init_net; +struct net init_net = { + .dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head), +}; EXPORT_SYMBOL(init_net); #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 05db410..207a178 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -357,22 +357,23 @@ EXPORT_SYMBOL(netpoll_send_skb_on_dev); void netpoll_send_udp(struct netpoll *np, const char *msg, int len) { - int total_len, eth_len, ip_len, udp_len; + int total_len, ip_len, udp_len; struct sk_buff *skb; struct udphdr *udph; struct iphdr *iph; struct ethhdr *eth; udp_len = len + sizeof(*udph); - ip_len = eth_len = udp_len + sizeof(*iph); - total_len = eth_len + ETH_HLEN + NET_IP_ALIGN; + ip_len = udp_len + sizeof(*iph); + total_len = ip_len + LL_RESERVED_SPACE(np->dev); - skb = find_skb(np, total_len, total_len - len); + skb = find_skb(np, total_len + np->dev->needed_tailroom, + total_len - len); if (!skb) return; skb_copy_to_linear_data(skb, msg, len); - skb->len += len; + skb_put(skb, len); skb_push(skb, sizeof(*udph)); skb_reset_transport_header(skb); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index e35a6fb..01890e1 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -1932,7 +1932,7 @@ static int pktgen_device_event(struct notifier_block *unused, { struct net_device *dev = ptr; - if (!net_eq(dev_net(dev), &init_net)) + if (!net_eq(dev_net(dev), &init_net) || pktgen_exiting) return NOTIFY_DONE; /* It is OK that we do not hold the group lock right now, @@ -2932,7 +2932,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, sizeof(struct ipv6hdr) - sizeof(struct udphdr) - pkt_dev->pkt_overhead; - if (datalen < sizeof(struct pktgen_hdr)) { + if (datalen < 0 || datalen < sizeof(struct pktgen_hdr)) { datalen = sizeof(struct pktgen_hdr); if (net_ratelimit()) pr_info("increased datalen to %d\n", datalen); @@ -3755,12 +3755,18 @@ static void __exit pg_cleanup(void) { struct pktgen_thread *t; struct list_head *q, *n; + LIST_HEAD(list); /* Stop all interfaces & threads */ pktgen_exiting = true; - list_for_each_safe(q, n, &pktgen_threads) { + mutex_lock(&pktgen_thread_lock); + list_splice_init(&pktgen_threads, &list); + mutex_unlock(&pktgen_thread_lock); + + list_for_each_safe(q, n, &list) { t = list_entry(q, struct pktgen_thread, th_list); + list_del(&t->th_list); kthread_stop(t->tsk); kfree(t); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index abd936d..ac49ad5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -647,6 +647,12 @@ static void set_operstate(struct net_device *dev, unsigned char transition) } } +static unsigned int rtnl_dev_get_flags(const struct net_device *dev) +{ + return (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI)) | + (dev->gflags & (IFF_PROMISC | IFF_ALLMULTI)); +} + static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, const struct ifinfomsg *ifm) { @@ -655,7 +661,7 @@ static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, /* bugwards compatibility: ifi_change == 0 is treated as ~0 */ if (ifm->ifi_change) flags = (flags & ifm->ifi_change) | - (dev->flags & ~ifm->ifi_change); + (rtnl_dev_get_flags(dev) & ~ifm->ifi_change); return flags; } @@ -1298,6 +1304,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, goto errout; send_addr_notify = 1; modified = 1; + add_device_randomness(dev->dev_addr, dev->addr_len); } if (tb[IFLA_MTU]) { diff --git a/net/core/sock.c b/net/core/sock.c index aebb419..3da11ba 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -594,7 +594,8 @@ set_rcvbuf: case SO_KEEPALIVE: #ifdef CONFIG_INET - if (sk->sk_protocol == IPPROTO_TCP) + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_type == SOCK_STREAM) tcp_set_keepalive(sk, valbool); #endif sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool); @@ -1312,6 +1313,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; sk->sk_gso_max_size = dst->dev->gso_max_size; + sk->sk_gso_max_segs = dst->dev->gso_max_segs; } } } @@ -1501,6 +1503,11 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, gfp_t gfp_mask; long timeo; int err; + int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT; + + err = -EMSGSIZE; + if (npages > MAX_SKB_FRAGS) + goto failure; gfp_mask = sk->sk_allocation; if (gfp_mask & __GFP_WAIT) @@ -1519,14 +1526,12 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { skb = alloc_skb(header_len, gfp_mask); if (skb) { - int npages; int i; /* No pages, we're done... */ if (!data_len) break; - npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT; skb->truesize += data_len; skb_shinfo(skb)->nr_frags = npages; for (i = 0; i < npages; i++) { |