--- zzzz-none-000/linux-3.10.107/drivers/net/macvlan.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/drivers/net/macvlan.c 2021-02-04 17:41:59.000000000 +0000 @@ -30,22 +30,56 @@ #include #include #include +#include #include #include +#include -#define MACVLAN_HASH_SIZE (1 << BITS_PER_BYTE) +#define MACVLAN_HASH_BITS 8 +#define MACVLAN_HASH_SIZE (1<cb[0])) + static void macvlan_port_destroy(struct net_device *dev); +/* Hash Ethernet address */ +static u32 macvlan_eth_hash(const unsigned char *addr) +{ + u64 value = get_unaligned((u64 *)addr); + + /* only want 6 bytes */ +#ifdef __BIG_ENDIAN + value >>= 16; +#else + value <<= 16; +#endif + return hash_64(value, MACVLAN_HASH_BITS); +} + static struct macvlan_port *macvlan_port_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->rx_handler_data); @@ -62,20 +96,68 @@ const unsigned char *addr) { struct macvlan_dev *vlan; + u32 idx = macvlan_eth_hash(addr); - hlist_for_each_entry_rcu(vlan, &port->vlan_hash[addr[5]], hlist) { + hlist_for_each_entry_rcu(vlan, &port->vlan_hash[idx], hlist) { if (ether_addr_equal_64bits(vlan->dev->dev_addr, addr)) return vlan; } return NULL; } +static struct macvlan_source_entry *macvlan_hash_lookup_source( + const struct macvlan_dev *vlan, + const unsigned char *addr) +{ + struct macvlan_source_entry *entry; + u32 idx = macvlan_eth_hash(addr); + struct hlist_head *h = &vlan->port->vlan_source_hash[idx]; + + hlist_for_each_entry_rcu(entry, h, hlist) { + if (ether_addr_equal_64bits(entry->addr, addr) && + entry->vlan == vlan) + return entry; + } + return NULL; +} + +static int macvlan_hash_add_source(struct macvlan_dev *vlan, + const unsigned char *addr) +{ + struct macvlan_port *port = vlan->port; + struct macvlan_source_entry *entry; + struct hlist_head *h; + + entry = macvlan_hash_lookup_source(vlan, addr); + if (entry) + return 0; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + ether_addr_copy(entry->addr, addr); + entry->vlan = vlan; + h = &port->vlan_source_hash[macvlan_eth_hash(addr)]; + hlist_add_head_rcu(&entry->hlist, h); + vlan->macaddr_count++; + + return 0; +} + static void macvlan_hash_add(struct macvlan_dev *vlan) { struct macvlan_port *port = vlan->port; const unsigned char *addr = vlan->dev->dev_addr; + u32 idx = macvlan_eth_hash(addr); + + hlist_add_head_rcu(&vlan->hlist, &port->vlan_hash[idx]); +} - hlist_add_head_rcu(&vlan->hlist, &port->vlan_hash[addr[5]]); +static void macvlan_hash_del_source(struct macvlan_source_entry *entry) +{ + hlist_del_rcu(&entry->hlist); + kfree_rcu(entry, rcu); } static void macvlan_hash_del(struct macvlan_dev *vlan, bool sync) @@ -118,11 +200,9 @@ const struct ethhdr *eth, bool local) { struct net_device *dev = vlan->dev; - if (!skb) - return NET_RX_DROP; if (local) - return vlan->forward(dev, skb); + return __dev_forward_skb(dev, skb); skb->dev = dev; if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) @@ -130,7 +210,7 @@ else skb->pkt_type = PACKET_MULTICAST; - return vlan->receive(skb); + return 0; } static u32 macvlan_hash_mix(const struct macvlan_dev *vlan) @@ -171,34 +251,38 @@ hash = mc_hash(vlan, eth->h_dest); if (!test_bit(hash, vlan->mc_filter)) continue; + + err = NET_RX_DROP; nskb = skb_clone(skb, GFP_ATOMIC); - err = macvlan_broadcast_one(nskb, vlan, eth, - mode == MACVLAN_MODE_BRIDGE); + if (likely(nskb)) + err = macvlan_broadcast_one( + nskb, vlan, eth, + mode == MACVLAN_MODE_BRIDGE) ?: + netif_rx_ni(nskb); macvlan_count_rx(vlan, skb->len + ETH_HLEN, - err == NET_RX_SUCCESS, 1); + err == NET_RX_SUCCESS, true); } } } -/* called under rcu_read_lock() from netif_receive_skb */ -static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) +static void macvlan_process_broadcast(struct work_struct *w) { - struct macvlan_port *port; - struct sk_buff *skb = *pskb; - const struct ethhdr *eth = eth_hdr(skb); - const struct macvlan_dev *vlan; - const struct macvlan_dev *src; - struct net_device *dev; - unsigned int len = 0; - int ret = NET_RX_DROP; + struct macvlan_port *port = container_of(w, struct macvlan_port, + bc_work); + struct sk_buff *skb; + struct sk_buff_head list; + + __skb_queue_head_init(&list); + + spin_lock_bh(&port->bc_queue.lock); + skb_queue_splice_tail_init(&port->bc_queue, &list); + spin_unlock_bh(&port->bc_queue.lock); + + while ((skb = __skb_dequeue(&list))) { + const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src; + + rcu_read_lock(); - port = macvlan_port_get_rcu(skb->dev); - if (is_multicast_ether_addr(eth->h_dest)) { - skb = ip_check_defrag(skb, IP_DEFRAG_MACVLAN); - if (!skb) - return RX_HANDLER_CONSUMED; - eth = eth_hdr(skb); - src = macvlan_hash_lookup(port, eth->h_source); if (!src) /* frame comes from an external address */ macvlan_broadcast(skb, port, NULL, @@ -211,23 +295,147 @@ macvlan_broadcast(skb, port, src->dev, MACVLAN_MODE_VEPA | MACVLAN_MODE_BRIDGE); - else if (src->mode == MACVLAN_MODE_BRIDGE) + else /* * flood only to VEPA ports, bridge ports * already saw the frame on the way out. */ macvlan_broadcast(skb, port, src->dev, MACVLAN_MODE_VEPA); - else { + + rcu_read_unlock(); + + kfree_skb(skb); + } +} + +static void macvlan_broadcast_enqueue(struct macvlan_port *port, + struct sk_buff *skb) +{ + struct sk_buff *nskb; + int err = -ENOMEM; + + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + goto err; + + spin_lock(&port->bc_queue.lock); + if (skb_queue_len(&port->bc_queue) < MACVLAN_BC_QUEUE_LEN) { + __skb_queue_tail(&port->bc_queue, nskb); + err = 0; + } + spin_unlock(&port->bc_queue.lock); + + if (err) + goto free_nskb; + + schedule_work(&port->bc_work); + return; + +free_nskb: + kfree_skb(nskb); +err: + atomic_long_inc(&skb->dev->rx_dropped); +} + +static void macvlan_flush_sources(struct macvlan_port *port, + struct macvlan_dev *vlan) +{ + int i; + + for (i = 0; i < MACVLAN_HASH_SIZE; i++) { + struct hlist_node *h, *n; + + hlist_for_each_safe(h, n, &port->vlan_source_hash[i]) { + struct macvlan_source_entry *entry; + + entry = hlist_entry(h, struct macvlan_source_entry, + hlist); + if (entry->vlan == vlan) + macvlan_hash_del_source(entry); + } + } + vlan->macaddr_count = 0; +} + +static void macvlan_forward_source_one(struct sk_buff *skb, + struct macvlan_dev *vlan) +{ + struct sk_buff *nskb; + struct net_device *dev; + int len; + int ret; + + dev = vlan->dev; + if (unlikely(!(dev->flags & IFF_UP))) + return; + + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return; + + len = nskb->len + ETH_HLEN; + nskb->dev = dev; + nskb->pkt_type = PACKET_HOST; + + ret = netif_rx(nskb); + macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false); +} + +static void macvlan_forward_source(struct sk_buff *skb, + struct macvlan_port *port, + const unsigned char *addr) +{ + struct macvlan_source_entry *entry; + u32 idx = macvlan_eth_hash(addr); + struct hlist_head *h = &port->vlan_source_hash[idx]; + + hlist_for_each_entry_rcu(entry, h, hlist) { + if (ether_addr_equal_64bits(entry->addr, addr)) + if (entry->vlan->dev->flags & IFF_UP) + macvlan_forward_source_one(skb, entry->vlan); + } +} + +/* called under rcu_read_lock() from netif_receive_skb */ +static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) +{ + struct macvlan_port *port; + struct sk_buff *skb = *pskb; + const struct ethhdr *eth = eth_hdr(skb); + const struct macvlan_dev *vlan; + const struct macvlan_dev *src; + struct net_device *dev; + unsigned int len = 0; + int ret; + rx_handler_result_t handle_res; + + port = macvlan_port_get_rcu(skb->dev); + if (is_multicast_ether_addr(eth->h_dest)) { + skb = ip_check_defrag(dev_net(skb->dev), skb, IP_DEFRAG_MACVLAN); + if (!skb) + return RX_HANDLER_CONSUMED; + *pskb = skb; + eth = eth_hdr(skb); + macvlan_forward_source(skb, port, eth->h_source); + src = macvlan_hash_lookup(port, eth->h_source); + if (src && src->mode != MACVLAN_MODE_VEPA && + src->mode != MACVLAN_MODE_BRIDGE) { /* forward to original port. */ vlan = src; - ret = macvlan_broadcast_one(skb, vlan, eth, 0); + ret = macvlan_broadcast_one(skb, vlan, eth, 0) ?: + netif_rx(skb); + handle_res = RX_HANDLER_CONSUMED; goto out; } + MACVLAN_SKB_CB(skb)->src = src; + macvlan_broadcast_enqueue(port, skb); + return RX_HANDLER_PASS; } + macvlan_forward_source(skb, port, eth->h_source); if (port->passthru) vlan = list_first_or_null_rcu(&port->vlans, struct macvlan_dev, list); @@ -243,17 +451,21 @@ } len = skb->len + ETH_HLEN; skb = skb_share_check(skb, GFP_ATOMIC); - if (!skb) + if (!skb) { + ret = NET_RX_DROP; + handle_res = RX_HANDLER_CONSUMED; goto out; + } + *pskb = skb; skb->dev = dev; skb->pkt_type = PACKET_HOST; - ret = vlan->receive(skb); - + ret = NET_RX_SUCCESS; + handle_res = RX_HANDLER_ANOTHER; out: - macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, 0); - return RX_HANDLER_CONSUMED; + macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false); + return handle_res; } static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) @@ -285,16 +497,36 @@ return dev_queue_xmit(skb); } -netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, - struct net_device *dev) +static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb) +{ +#ifdef CONFIG_NET_POLL_CONTROLLER + if (vlan->netpoll) + netpoll_send_skb(vlan->netpoll, skb); +#else + BUG(); +#endif + return NETDEV_TX_OK; +} + +static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, + struct net_device *dev) { unsigned int len = skb->len; int ret; - const struct macvlan_dev *vlan = netdev_priv(dev); + struct macvlan_dev *vlan = netdev_priv(dev); + + if (unlikely(netpoll_tx_running(dev))) + return macvlan_netpoll_send_skb(vlan, skb); + + if (vlan->fwd_priv) { + skb->dev = vlan->lowerdev; + ret = dev_queue_xmit_accel(skb, vlan->fwd_priv); + } else { + ret = macvlan_queue_xmit(skb, dev); + } - ret = macvlan_queue_xmit(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { - struct macvlan_pcpu_stats *pcpu_stats; + struct vlan_pcpu_stats *pcpu_stats; pcpu_stats = this_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); @@ -306,7 +538,6 @@ } return ret; } -EXPORT_SYMBOL_GPL(macvlan_start_xmit); static int macvlan_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, @@ -321,12 +552,13 @@ static const struct header_ops macvlan_hard_header_ops = { .create = macvlan_hard_header, - .rebuild = eth_rebuild_header, .parse = eth_header_parse, .cache = eth_header_cache, .cache_update = eth_header_cache_update, }; +static struct rtnl_link_ops macvlan_link_ops; + static int macvlan_open(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); @@ -334,11 +566,28 @@ int err; if (vlan->port->passthru) { - if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) - dev_set_promiscuity(lowerdev, 1); + if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) { + err = dev_set_promiscuity(lowerdev, 1); + if (err < 0) + goto out; + } goto hash_add; } + if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD && + dev->rtnl_link_ops == &macvlan_link_ops) { + vlan->fwd_priv = + lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev); + + /* If we get a NULL pointer back, or if we get an error + * then we should just fall through to the non accelerated path + */ + if (IS_ERR_OR_NULL(vlan->fwd_priv)) { + vlan->fwd_priv = NULL; + } else + return 0; + } + err = -EBUSY; if (macvlan_addr_busy(vlan->port, dev->dev_addr)) goto out; @@ -352,13 +601,26 @@ goto del_unicast; } + if (dev->flags & IFF_PROMISC) { + err = dev_set_promiscuity(lowerdev, 1); + if (err < 0) + goto clear_multi; + } + hash_add: macvlan_hash_add(vlan); return 0; +clear_multi: + dev_set_allmulti(lowerdev, -1); del_unicast: dev_uc_del(lowerdev, dev->dev_addr); out: + if (vlan->fwd_priv) { + lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, + vlan->fwd_priv); + vlan->fwd_priv = NULL; + } return err; } @@ -367,6 +629,13 @@ struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; + if (vlan->fwd_priv) { + lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, + vlan->fwd_priv); + vlan->fwd_priv = NULL; + return 0; + } + dev_uc_unsync(lowerdev, dev); dev_mc_unsync(lowerdev, dev); @@ -379,6 +648,9 @@ if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(lowerdev, -1); + if (dev->flags & IFF_PROMISC) + dev_set_promiscuity(lowerdev, -1); + dev_uc_del(lowerdev, dev->dev_addr); hash_del: @@ -386,35 +658,49 @@ return 0; } -static int macvlan_set_mac_address(struct net_device *dev, void *p) +static int macvlan_sync_address(struct net_device *dev, unsigned char *addr) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; - struct sockaddr *addr = p; int err; - if (!is_valid_ether_addr(addr->sa_data)) - return -EADDRNOTAVAIL; - if (!(dev->flags & IFF_UP)) { /* Just copy in the new address */ - memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); + ether_addr_copy(dev->dev_addr, addr); } else { /* Rehash and update the device filters */ - if (macvlan_addr_busy(vlan->port, addr->sa_data)) + if (macvlan_addr_busy(vlan->port, addr)) return -EBUSY; - err = dev_uc_add(lowerdev, addr->sa_data); - if (err) - return err; + if (!vlan->port->passthru) { + err = dev_uc_add(lowerdev, addr); + if (err) + return err; - dev_uc_del(lowerdev, dev->dev_addr); + dev_uc_del(lowerdev, dev->dev_addr); + } - macvlan_hash_change_addr(vlan, addr->sa_data); + macvlan_hash_change_addr(vlan, addr); } return 0; } +static int macvlan_set_mac_address(struct net_device *dev, void *p) +{ + struct macvlan_dev *vlan = netdev_priv(dev); + struct sockaddr *addr = p; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + if (vlan->mode == MACVLAN_MODE_PASSTHRU) { + dev_set_mac_address(vlan->lowerdev, addr); + return 0; + } + + return macvlan_sync_address(dev, addr->sa_data); +} + static void macvlan_change_rx_flags(struct net_device *dev, int change) { struct macvlan_dev *vlan = netdev_priv(dev); @@ -423,6 +709,10 @@ if (dev->flags & IFF_UP) { if (change & IFF_ALLMULTI) dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1); + if (change & IFF_PROMISC) + dev_set_promiscuity(lowerdev, + dev->flags & IFF_PROMISC ? 1 : -1); + } } @@ -467,15 +757,24 @@ static struct lock_class_key macvlan_netdev_xmit_lock_key; static struct lock_class_key macvlan_netdev_addr_lock_key; +#define ALWAYS_ON_FEATURES \ + (NETIF_F_SG | NETIF_F_GEN_CSUM | NETIF_F_GSO_SOFTWARE | NETIF_F_LLTX | \ + NETIF_F_GSO_ROBUST) + #define MACVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_ALL_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ - NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_GSO_ROBUST | \ + NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_LRO | \ NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_GRO | NETIF_F_RXCSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER) #define MACVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) +static int macvlan_get_nest_level(struct net_device *dev) +{ + return ((struct macvlan_dev *)netdev_priv(dev))->nest_level; +} + static void macvlan_set_lockdep_class_one(struct net_device *dev, struct netdev_queue *txq, void *_unused) @@ -486,8 +785,9 @@ static void macvlan_set_lockdep_class(struct net_device *dev) { - lockdep_set_class(&dev->addr_list_lock, - &macvlan_netdev_addr_lock_key); + lockdep_set_class_and_subclass(&dev->addr_list_lock, + &macvlan_netdev_addr_lock_key, + macvlan_get_nest_level(dev)); netdev_for_each_tx_queue(dev, macvlan_set_lockdep_class_one, NULL); } @@ -499,15 +799,15 @@ dev->state = (dev->state & ~MACVLAN_STATE_MASK) | (lowerdev->state & MACVLAN_STATE_MASK); dev->features = lowerdev->features & MACVLAN_FEATURES; - dev->features |= NETIF_F_LLTX; + dev->features |= ALWAYS_ON_FEATURES; + dev->hw_features |= NETIF_F_LRO; dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES; dev->gso_max_size = lowerdev->gso_max_size; - dev->iflink = lowerdev->ifindex; dev->hard_header_len = lowerdev->hard_header_len; macvlan_set_lockdep_class(dev); - vlan->pcpu_stats = alloc_percpu(struct macvlan_pcpu_stats); + vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->pcpu_stats) return -ENOMEM; @@ -521,6 +821,7 @@ free_percpu(vlan->pcpu_stats); + macvlan_flush_sources(port, vlan); port->count -= 1; if (!port->count) macvlan_port_destroy(port->dev); @@ -532,7 +833,7 @@ struct macvlan_dev *vlan = netdev_priv(dev); if (vlan->pcpu_stats) { - struct macvlan_pcpu_stats *p; + struct vlan_pcpu_stats *p; u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes; u32 rx_errors = 0, tx_dropped = 0; unsigned int start; @@ -541,13 +842,13 @@ for_each_possible_cpu(i) { p = per_cpu_ptr(vlan->pcpu_stats, i); do { - start = u64_stats_fetch_begin_bh(&p->syncp); + start = u64_stats_fetch_begin_irq(&p->syncp); rx_packets = p->rx_packets; rx_bytes = p->rx_bytes; rx_multicast = p->rx_multicast; tx_packets = p->tx_packets; tx_bytes = p->tx_bytes; - } while (u64_stats_fetch_retry_bh(&p->syncp, start)); + } while (u64_stats_fetch_retry_irq(&p->syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; @@ -588,13 +889,19 @@ static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr, + const unsigned char *addr, u16 vid, u16 flags) { struct macvlan_dev *vlan = netdev_priv(dev); int err = -EINVAL; - if (!vlan->port->passthru) + /* Support unicast filter only on passthru devices. + * Multicast filter should be allowed on all devices. + */ + if (!vlan->port->passthru && is_unicast_ether_addr(addr)) + return -EOPNOTSUPP; + + if (flags & NLM_F_REPLACE) return -EOPNOTSUPP; if (is_unicast_ether_addr(addr)) @@ -607,12 +914,15 @@ static int macvlan_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr) + const unsigned char *addr, u16 vid) { struct macvlan_dev *vlan = netdev_priv(dev); int err = -EINVAL; - if (!vlan->port->passthru) + /* Support unicast filter only on passthru devices. + * Multicast filter should be allowed on all devices. + */ + if (!vlan->port->passthru && is_unicast_ether_addr(addr)) return -EOPNOTSUPP; if (is_unicast_ether_addr(addr)) @@ -638,6 +948,76 @@ return __ethtool_get_settings(vlan->lowerdev, cmd); } +static netdev_features_t macvlan_fix_features(struct net_device *dev, + netdev_features_t features) +{ + struct macvlan_dev *vlan = netdev_priv(dev); + netdev_features_t lowerdev_features = vlan->lowerdev->features; + netdev_features_t mask; + + features |= NETIF_F_ALL_FOR_ALL; + features &= (vlan->set_features | ~MACVLAN_FEATURES); + mask = features; + + lowerdev_features &= (features | ~NETIF_F_LRO); + features = netdev_increment_features(lowerdev_features, features, mask); + features |= ALWAYS_ON_FEATURES; + features &= ~NETIF_F_NETNS_LOCAL; + + return features; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +static void macvlan_dev_poll_controller(struct net_device *dev) +{ + return; +} + +static int macvlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo) +{ + struct macvlan_dev *vlan = netdev_priv(dev); + struct net_device *real_dev = vlan->lowerdev; + struct netpoll *netpoll; + int err = 0; + + netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); + err = -ENOMEM; + if (!netpoll) + goto out; + + err = __netpoll_setup(netpoll, real_dev); + if (err) { + kfree(netpoll); + goto out; + } + + vlan->netpoll = netpoll; + +out: + return err; +} + +static void macvlan_dev_netpoll_cleanup(struct net_device *dev) +{ + struct macvlan_dev *vlan = netdev_priv(dev); + struct netpoll *netpoll = vlan->netpoll; + + if (!netpoll) + return; + + vlan->netpoll = NULL; + + __netpoll_free_async(netpoll); +} +#endif /* CONFIG_NET_POLL_CONTROLLER */ + +static int macvlan_dev_get_iflink(const struct net_device *dev) +{ + struct macvlan_dev *vlan = netdev_priv(dev); + + return vlan->lowerdev->ifindex; +} + static const struct ethtool_ops macvlan_ethtool_ops = { .get_link = ethtool_op_get_link, .get_settings = macvlan_ethtool_get_settings, @@ -651,6 +1031,7 @@ .ndo_stop = macvlan_stop, .ndo_start_xmit = macvlan_start_xmit, .ndo_change_mtu = macvlan_change_mtu, + .ndo_fix_features = macvlan_fix_features, .ndo_change_rx_flags = macvlan_change_rx_flags, .ndo_set_mac_address = macvlan_set_mac_address, .ndo_set_rx_mode = macvlan_set_mac_lists, @@ -661,17 +1042,26 @@ .ndo_fdb_add = macvlan_fdb_add, .ndo_fdb_del = macvlan_fdb_del, .ndo_fdb_dump = ndo_dflt_fdb_dump, + .ndo_get_lock_subclass = macvlan_get_nest_level, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = macvlan_dev_poll_controller, + .ndo_netpoll_setup = macvlan_dev_netpoll_setup, + .ndo_netpoll_cleanup = macvlan_dev_netpoll_cleanup, +#endif + .ndo_get_iflink = macvlan_dev_get_iflink, + .ndo_features_check = passthru_features_check, }; void macvlan_common_setup(struct net_device *dev) { ether_setup(dev); - dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + netif_keep_dst(dev); dev->priv_flags |= IFF_UNICAST_FLT; dev->netdev_ops = &macvlan_netdev_ops; dev->destructor = free_netdev; - dev->header_ops = &macvlan_hard_header_ops, + dev->header_ops = &macvlan_hard_header_ops; dev->ethtool_ops = &macvlan_ethtool_ops; } EXPORT_SYMBOL_GPL(macvlan_common_setup); @@ -691,6 +1081,9 @@ if (dev->type != ARPHRD_ETHER || dev->flags & IFF_LOOPBACK) return -EINVAL; + if (netif_is_ipvlan_port(dev)) + return -EBUSY; + port = kzalloc(sizeof(*port), GFP_KERNEL); if (port == NULL) return -ENOMEM; @@ -700,6 +1093,11 @@ INIT_LIST_HEAD(&port->vlans); for (i = 0; i < MACVLAN_HASH_SIZE; i++) INIT_HLIST_HEAD(&port->vlan_hash[i]); + for (i = 0; i < MACVLAN_HASH_SIZE; i++) + INIT_HLIST_HEAD(&port->vlan_source_hash[i]); + + skb_queue_head_init(&port->bc_queue); + INIT_WORK(&port->bc_work, macvlan_process_broadcast); err = netdev_rx_handler_register(dev, macvlan_handle_frame, port); if (err) @@ -715,6 +1113,13 @@ dev->priv_flags &= ~IFF_MACVLAN_PORT; netdev_rx_handler_unregister(dev); + + /* After this point, no packet can schedule bc_work anymore, + * but we need to cancel it and purge left skbs if any. + */ + cancel_work_sync(&port->bc_work); + __skb_queue_purge(&port->bc_queue); + kfree_rcu(port, rcu); } @@ -737,24 +1142,113 @@ case MACVLAN_MODE_VEPA: case MACVLAN_MODE_BRIDGE: case MACVLAN_MODE_PASSTHRU: + case MACVLAN_MODE_SOURCE: + break; + default: + return -EINVAL; + } + } + + if (data && data[IFLA_MACVLAN_MACADDR_MODE]) { + switch (nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE])) { + case MACVLAN_MACADDR_ADD: + case MACVLAN_MACADDR_DEL: + case MACVLAN_MACADDR_FLUSH: + case MACVLAN_MACADDR_SET: break; default: return -EINVAL; } } + + if (data && data[IFLA_MACVLAN_MACADDR]) { + if (nla_len(data[IFLA_MACVLAN_MACADDR]) != ETH_ALEN) + return -EINVAL; + + if (!is_valid_ether_addr(nla_data(data[IFLA_MACVLAN_MACADDR]))) + return -EADDRNOTAVAIL; + } + + if (data && data[IFLA_MACVLAN_MACADDR_COUNT]) + return -EINVAL; + + return 0; +} + +/** + * reconfigure list of remote source mac address + * (only for macvlan devices in source mode) + * Note regarding alignment: all netlink data is aligned to 4 Byte, which + * suffices for both ether_addr_copy and ether_addr_equal_64bits usage. + */ +static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode, + struct nlattr *data[]) +{ + char *addr = NULL; + int ret, rem, len; + struct nlattr *nla, *head; + struct macvlan_source_entry *entry; + + if (data[IFLA_MACVLAN_MACADDR]) + addr = nla_data(data[IFLA_MACVLAN_MACADDR]); + + if (mode == MACVLAN_MACADDR_ADD) { + if (!addr) + return -EINVAL; + + return macvlan_hash_add_source(vlan, addr); + + } else if (mode == MACVLAN_MACADDR_DEL) { + if (!addr) + return -EINVAL; + + entry = macvlan_hash_lookup_source(vlan, addr); + if (entry) { + macvlan_hash_del_source(entry); + vlan->macaddr_count--; + } + } else if (mode == MACVLAN_MACADDR_FLUSH) { + macvlan_flush_sources(vlan->port, vlan); + } else if (mode == MACVLAN_MACADDR_SET) { + macvlan_flush_sources(vlan->port, vlan); + + if (addr) { + ret = macvlan_hash_add_source(vlan, addr); + if (ret) + return ret; + } + + if (!data || !data[IFLA_MACVLAN_MACADDR_DATA]) + return 0; + + head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]); + len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]); + + nla_for_each_attr(nla, head, len, rem) { + if (nla_type(nla) != IFLA_MACVLAN_MACADDR || + nla_len(nla) != ETH_ALEN) + continue; + + addr = nla_data(nla); + ret = macvlan_hash_add_source(vlan, addr); + if (ret) + return ret; + } + } else { + return -EINVAL; + } + return 0; } int macvlan_common_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], - int (*receive)(struct sk_buff *skb), - int (*forward)(struct net_device *dev, - struct sk_buff *skb)) + struct nlattr *tb[], struct nlattr *data[]) { struct macvlan_dev *vlan = netdev_priv(dev); struct macvlan_port *port; struct net_device *lowerdev; int err; + int macmode; if (!tb[IFLA_LINK]) return -EINVAL; @@ -763,13 +1257,11 @@ if (lowerdev == NULL) return -ENODEV; - /* When creating macvlans on top of other macvlans - use + /* When creating macvlans or macvtaps on top of other macvlans - use * the real device as the lowerdev. */ - if (lowerdev->rtnl_link_ops == dev->rtnl_link_ops) { - struct macvlan_dev *lowervlan = netdev_priv(lowerdev); - lowerdev = lowervlan->lowerdev; - } + if (netif_is_macvlan(lowerdev)) + lowerdev = macvlan_dev_real_dev(lowerdev); if (!tb[IFLA_MTU]) dev->mtu = lowerdev->mtu; @@ -793,8 +1285,8 @@ vlan->lowerdev = lowerdev; vlan->dev = dev; vlan->port = port; - vlan->receive = receive; - vlan->forward = forward; + vlan->set_features = MACVLAN_FEATURES; + vlan->nest_level = dev_get_nest_level(lowerdev, netif_is_macvlan) + 1; vlan->mode = MACVLAN_MODE_VEPA; if (data && data[IFLA_MACVLAN_MODE]) @@ -807,25 +1299,35 @@ if (port->count) return -EINVAL; port->passthru = true; - memcpy(dev->dev_addr, lowerdev->dev_addr, ETH_ALEN); + eth_hw_addr_inherit(dev, lowerdev); } - err = netdev_upper_dev_link(lowerdev, dev); - if (err) - goto destroy_port; + if (data && data[IFLA_MACVLAN_MACADDR_MODE]) { + if (vlan->mode != MACVLAN_MODE_SOURCE) + return -EINVAL; + macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]); + err = macvlan_changelink_sources(vlan, macmode, data); + if (err) + return err; + } port->count += 1; err = register_netdevice(dev); if (err < 0) - goto upper_dev_unlink; + goto destroy_port; + + dev->priv_flags |= IFF_MACVLAN; + err = netdev_upper_dev_link(lowerdev, dev); + if (err) + goto unregister_netdev; list_add_tail_rcu(&vlan->list, &port->vlans); netif_stacked_transfer_operstate(lowerdev, dev); return 0; -upper_dev_unlink: - netdev_upper_dev_unlink(lowerdev, dev); +unregister_netdev: + unregister_netdevice(dev); destroy_port: port->count -= 1; if (!port->count) @@ -838,15 +1340,15 @@ static int macvlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - return macvlan_common_newlink(src_net, dev, tb, data, - netif_rx, - dev_forward_skb); + return macvlan_common_newlink(src_net, dev, tb, data); } void macvlan_dellink(struct net_device *dev, struct list_head *head) { struct macvlan_dev *vlan = netdev_priv(dev); + if (vlan->mode == MACVLAN_MODE_SOURCE) + macvlan_flush_sources(vlan->port, vlan); list_del_rcu(&vlan->list); unregister_netdevice_queue(dev, head); netdev_upper_dev_unlink(vlan->lowerdev, dev); @@ -857,6 +1359,23 @@ struct nlattr *tb[], struct nlattr *data[]) { struct macvlan_dev *vlan = netdev_priv(dev); + enum macvlan_mode mode; + bool set_mode = false; + enum macvlan_macaddr_mode macmode; + int ret; + + /* Validate mode, but don't set yet: setting flags may fail. */ + if (data && data[IFLA_MACVLAN_MODE]) { + set_mode = true; + mode = nla_get_u32(data[IFLA_MACVLAN_MODE]); + /* Passthrough mode can't be set or cleared dynamically */ + if ((mode == MACVLAN_MODE_PASSTHRU) != + (vlan->mode == MACVLAN_MODE_PASSTHRU)) + return -EINVAL; + if (vlan->mode == MACVLAN_MODE_SOURCE && + vlan->mode != mode) + macvlan_flush_sources(vlan->port, vlan); + } if (data && data[IFLA_MACVLAN_FLAGS]) { __u16 flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]); @@ -873,28 +1392,79 @@ } vlan->flags = flags; } - if (data && data[IFLA_MACVLAN_MODE]) - vlan->mode = nla_get_u32(data[IFLA_MACVLAN_MODE]); + if (set_mode) + vlan->mode = mode; + if (data && data[IFLA_MACVLAN_MACADDR_MODE]) { + if (vlan->mode != MACVLAN_MODE_SOURCE) + return -EINVAL; + macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]); + ret = macvlan_changelink_sources(vlan, macmode, data); + if (ret) + return ret; + } return 0; } +static size_t macvlan_get_size_mac(const struct macvlan_dev *vlan) +{ + if (vlan->macaddr_count == 0) + return 0; + return nla_total_size(0) /* IFLA_MACVLAN_MACADDR_DATA */ + + vlan->macaddr_count * nla_total_size(sizeof(u8) * ETH_ALEN); +} + static size_t macvlan_get_size(const struct net_device *dev) { + struct macvlan_dev *vlan = netdev_priv(dev); + return (0 + nla_total_size(4) /* IFLA_MACVLAN_MODE */ + nla_total_size(2) /* IFLA_MACVLAN_FLAGS */ + + nla_total_size(4) /* IFLA_MACVLAN_MACADDR_COUNT */ + + macvlan_get_size_mac(vlan) /* IFLA_MACVLAN_MACADDR */ ); } +static int macvlan_fill_info_macaddr(struct sk_buff *skb, + const struct macvlan_dev *vlan, + const int i) +{ + struct hlist_head *h = &vlan->port->vlan_source_hash[i]; + struct macvlan_source_entry *entry; + + hlist_for_each_entry_rcu(entry, h, hlist) { + if (entry->vlan != vlan) + continue; + if (nla_put(skb, IFLA_MACVLAN_MACADDR, ETH_ALEN, entry->addr)) + return 1; + } + return 0; +} + static int macvlan_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); + int i; + struct nlattr *nest; if (nla_put_u32(skb, IFLA_MACVLAN_MODE, vlan->mode)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_MACVLAN_FLAGS, vlan->flags)) goto nla_put_failure; + if (nla_put_u32(skb, IFLA_MACVLAN_MACADDR_COUNT, vlan->macaddr_count)) + goto nla_put_failure; + if (vlan->macaddr_count > 0) { + nest = nla_nest_start(skb, IFLA_MACVLAN_MACADDR_DATA); + if (nest == NULL) + goto nla_put_failure; + + for (i = 0; i < MACVLAN_HASH_SIZE; i++) { + if (macvlan_fill_info_macaddr(skb, vlan, i)) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + } return 0; nla_put_failure: @@ -904,6 +1474,10 @@ static const struct nla_policy macvlan_policy[IFLA_MACVLAN_MAX + 1] = { [IFLA_MACVLAN_MODE] = { .type = NLA_U32 }, [IFLA_MACVLAN_FLAGS] = { .type = NLA_U16 }, + [IFLA_MACVLAN_MACADDR_MODE] = { .type = NLA_U32 }, + [IFLA_MACVLAN_MACADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, + [IFLA_MACVLAN_MACADDR_DATA] = { .type = NLA_NESTED }, + [IFLA_MACVLAN_MACADDR_COUNT] = { .type = NLA_U32 }, }; int macvlan_link_register(struct rtnl_link_ops *ops) @@ -921,17 +1495,23 @@ }; EXPORT_SYMBOL_GPL(macvlan_link_register); +static struct net *macvlan_get_link_net(const struct net_device *dev) +{ + return dev_net(macvlan_dev_real_dev(dev)); +} + static struct rtnl_link_ops macvlan_link_ops = { .kind = "macvlan", .setup = macvlan_setup, .newlink = macvlan_newlink, .dellink = macvlan_dellink, + .get_link_net = macvlan_get_link_net, }; static int macvlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = ptr; + struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct macvlan_dev *vlan, *next; struct macvlan_port *port; LIST_HEAD(list_kill); @@ -949,11 +1529,29 @@ break; case NETDEV_FEAT_CHANGE: list_for_each_entry(vlan, &port->vlans, list) { - vlan->dev->features = dev->features & MACVLAN_FEATURES; vlan->dev->gso_max_size = dev->gso_max_size; - netdev_features_change(vlan->dev); + netdev_update_features(vlan->dev); } break; + case NETDEV_CHANGEMTU: + list_for_each_entry(vlan, &port->vlans, list) { + if (vlan->dev->mtu <= dev->mtu) + continue; + dev_set_mtu(vlan->dev, dev->mtu); + } + break; + case NETDEV_CHANGEADDR: + if (!port->passthru) + return NOTIFY_DONE; + + vlan = list_first_entry_or_null(&port->vlans, + struct macvlan_dev, + list); + + if (macvlan_sync_address(vlan->dev, dev->dev_addr)) + return NOTIFY_BAD; + + break; case NETDEV_UNREGISTER: /* twiddle thumbs on netns device moves */ if (dev->reg_state != NETREG_UNREGISTERING) @@ -966,6 +1564,13 @@ case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlaying device to change its type. */ return NOTIFY_BAD; + + case NETDEV_NOTIFY_PEERS: + case NETDEV_BONDING_FAILOVER: + case NETDEV_RESEND_IGMP: + /* Propagate to all vlans */ + list_for_each_entry(vlan, &port->vlans, list) + call_netdevice_notifiers(event, vlan->dev); } return NOTIFY_DONE; }