diff options
Diffstat (limited to 'drivers/net/ipvlan')
| -rw-r--r-- | drivers/net/ipvlan/ipvlan.h | 3 | ||||
| -rw-r--r-- | drivers/net/ipvlan/ipvlan_core.c | 99 | ||||
| -rw-r--r-- | drivers/net/ipvlan/ipvlan_l3s.c | 12 | ||||
| -rw-r--r-- | drivers/net/ipvlan/ipvlan_main.c | 47 | ||||
| -rw-r--r-- | drivers/net/ipvlan/ipvtap.c | 8 |
5 files changed, 110 insertions, 59 deletions
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index 025e0c19ec25..50de3ee204db 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -166,8 +166,7 @@ struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type); void ipvlan_count_rx(const struct ipvl_dev *ipvlan, unsigned int len, bool success, bool mcast); -int ipvlan_link_new(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack); void ipvlan_link_delete(struct net_device *dev, struct list_head *head); void ipvlan_link_setup(struct net_device *dev); diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index bb1c298c1e78..dea411e132db 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -2,6 +2,9 @@ /* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com> */ +#include <net/flow.h> +#include <net/ip.h> + #include "ipvlan.h" static u32 ipvlan_jhash_secret __read_mostly; @@ -49,8 +52,8 @@ static u8 ipvlan_get_v4_hash(const void *iaddr) { const struct in_addr *ip4_addr = iaddr; - return jhash_1word(ip4_addr->s_addr, ipvlan_jhash_secret) & - IPVLAN_HASH_MASK; + return jhash_1word((__force u32)ip4_addr->s_addr, ipvlan_jhash_secret) & + IPVLAN_HASH_MASK; } static bool addr_equal(bool is_v6, struct ipvl_addr *addr, const void *iaddr) @@ -157,7 +160,7 @@ void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type) return NULL; ip4h = ip_hdr(skb); - pktlen = ntohs(ip4h->tot_len); + pktlen = skb_ip_totlen(skb); if (ip4h->ihl < 5 || ip4h->version != 4) return NULL; if (skb->len < pktlen || pktlen < (ip4h->ihl * 4)) @@ -216,7 +219,7 @@ void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type) unsigned int ipvlan_mac_hash(const unsigned char *addr) { - u32 hash = jhash_1word(__get_unaligned_cpu32(addr+2), + u32 hash = jhash_1word(get_unaligned((u32 *)(addr + 2)), ipvlan_jhash_secret); return hash & IPVLAN_MAC_FILTER_MASK; @@ -411,22 +414,27 @@ struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, return addr; } -static int ipvlan_process_v4_outbound(struct sk_buff *skb) +static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb) { - const struct iphdr *ip4h = ip_hdr(skb); struct net_device *dev = skb->dev; struct net *net = dev_net(dev); - struct rtable *rt; int err, ret = NET_XMIT_DROP; + const struct iphdr *ip4h; + struct rtable *rt; struct flowi4 fl4 = { .flowi4_oif = dev->ifindex, - .flowi4_tos = RT_TOS(ip4h->tos), .flowi4_flags = FLOWI_FLAG_ANYSRC, .flowi4_mark = skb->mark, - .daddr = ip4h->daddr, - .saddr = ip4h->saddr, }; + if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) + goto err; + + ip4h = ip_hdr(skb); + fl4.daddr = ip4h->daddr; + fl4.saddr = ip4h->saddr; + fl4.flowi4_dscp = ip4h_dscp(ip4h); + rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto err; @@ -436,27 +444,28 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb) goto err; } skb_dst_set(skb, &rt->dst); - err = ip_local_out(net, skb->sk, skb); + + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + + err = ip_local_out(net, NULL, skb); if (unlikely(net_xmit_eval(err))) - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; goto out; err: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); out: return ret; } #if IS_ENABLED(CONFIG_IPV6) -static int ipvlan_process_v6_outbound(struct sk_buff *skb) + +static noinline_for_stack int +ipvlan_route_v6_outbound(struct net_device *dev, struct sk_buff *skb) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); - struct net_device *dev = skb->dev; - struct net *net = dev_net(dev); - struct dst_entry *dst; - int err, ret = NET_XMIT_DROP; struct flowi6 fl6 = { .flowi6_oif = dev->ifindex, .daddr = ip6h->daddr, @@ -466,24 +475,44 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) .flowi6_mark = skb->mark, .flowi6_proto = ip6h->nexthdr, }; + struct dst_entry *dst; + int err; - dst = ip6_route_output(net, NULL, &fl6); - if (dst->error) { - ret = dst->error; + dst = ip6_route_output(dev_net(dev), NULL, &fl6); + err = dst->error; + if (err) { dst_release(dst); - goto err; + return err; } skb_dst_set(skb, dst); - err = ip6_local_out(net, skb->sk, skb); + return 0; +} + +static int ipvlan_process_v6_outbound(struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + int err, ret = NET_XMIT_DROP; + + if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) { + DEV_STATS_INC(dev, tx_errors); + kfree_skb(skb); + return ret; + } + + err = ipvlan_route_v6_outbound(dev, skb); + if (unlikely(err)) { + DEV_STATS_INC(dev, tx_errors); + kfree_skb(skb); + return err; + } + + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + + err = ip6_local_out(dev_net(dev), NULL, skb); if (unlikely(net_xmit_eval(err))) - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; - goto out; -err: - dev->stats.tx_errors++; - kfree_skb(skb); -out: return ret; } #else @@ -549,8 +578,7 @@ static void ipvlan_multicast_enqueue(struct ipvl_port *port, spin_lock(&port->backlog.lock); if (skb_queue_len(&port->backlog) < IPVLAN_QBACKLOG_LIMIT) { - if (skb->dev) - dev_hold(skb->dev); + dev_hold(skb->dev); __skb_queue_tail(&port->backlog, skb); spin_unlock(&port->backlog.lock); schedule_work(&port->wq); @@ -579,7 +607,8 @@ static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev) consume_skb(skb); return NET_XMIT_DROP; } - return ipvlan_rcv_frame(addr, &skb, true); + ipvlan_rcv_frame(addr, &skb, true); + return NET_XMIT_SUCCESS; } } out: @@ -605,7 +634,8 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) consume_skb(skb); return NET_XMIT_DROP; } - return ipvlan_rcv_frame(addr, &skb, true); + ipvlan_rcv_frame(addr, &skb, true); + return NET_XMIT_SUCCESS; } } skb = skb_share_check(skb, GFP_ATOMIC); @@ -617,7 +647,8 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) * the skb for the main-dev. At the RX side we just return * RX_PASS for it to be processed further on the stack. */ - return dev_forward_skb(ipvlan->phy_dev, skb); + dev_forward_skb(ipvlan->phy_dev, skb); + return NET_XMIT_SUCCESS; } else if (is_multicast_ether_addr(eth->h_dest)) { skb_reset_mac_header(skb); diff --git a/drivers/net/ipvlan/ipvlan_l3s.c b/drivers/net/ipvlan/ipvlan_l3s.c index 943d26cbf39f..7c017fe35522 100644 --- a/drivers/net/ipvlan/ipvlan_l3s.c +++ b/drivers/net/ipvlan/ipvlan_l3s.c @@ -2,6 +2,8 @@ /* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com> */ +#include <net/ip.h> + #include "ipvlan.h" static unsigned int ipvlan_netid __read_mostly; @@ -48,11 +50,11 @@ static struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, switch (proto) { case AF_INET: { - struct iphdr *ip4h = ip_hdr(skb); + const struct iphdr *ip4h = ip_hdr(skb); int err; err = ip_route_input_noref(skb, ip4h->daddr, ip4h->saddr, - ip4h->tos, sdev); + ip4h_dscp(ip4h), sdev); if (unlikely(err)) goto out; break; @@ -101,6 +103,11 @@ static unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, goto out; skb->dev = addr->master->dev; + skb->skb_iif = skb->dev->ifindex; +#if IS_ENABLED(CONFIG_IPV6) + if (addr->atype == IPVL_IPV6) + IP6CB(skb)->iif = skb->dev->ifindex; +#endif len = skb->len + ETH_HLEN; ipvlan_count_rx(addr->master, len, true, false); out: @@ -219,5 +226,4 @@ void ipvlan_l3s_unregister(struct ipvl_port *port) dev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER; ipvlan_unregister_nf_hook(read_pnet(&port->pnet)); - dev->l3mdev_ops = NULL; } diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index b15dd9a3ad54..660f3db11766 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -3,6 +3,7 @@ */ #include <linux/ethtool.h> +#include <net/netdev_lock.h> #include "ipvlan.h" @@ -114,7 +115,7 @@ static void ipvlan_port_destroy(struct net_device *dev) NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL) #define IPVLAN_ALWAYS_ON \ - (IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED) + (IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_VLAN_CHALLENGED) #define IPVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ @@ -141,6 +142,7 @@ static int ipvlan_init(struct net_device *dev) dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES; dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS; dev->hw_enc_features |= dev->features; + dev->lltx = true; netif_inherit_tso_max(dev, phy_dev); dev->hard_header_len = phy_dev->hard_header_len; @@ -324,6 +326,7 @@ static void ipvlan_get_stats64(struct net_device *dev, s->rx_dropped = rx_errs; s->tx_dropped = tx_drps; } + s->tx_errors = DEV_STATS_READ(dev, tx_errors); } static int ipvlan_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) @@ -348,7 +351,7 @@ static int ipvlan_get_iflink(const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); - return ipvlan->phy_dev->ifindex; + return READ_ONCE(ipvlan->phy_dev->ifindex); } static const struct net_device_ops ipvlan_netdev_ops = { @@ -386,6 +389,7 @@ static const struct header_ops ipvlan_header_ops = { .parse = eth_header_parse, .cache = eth_header_cache, .cache_update = eth_header_cache_update, + .parse_protocol = eth_header_parse_protocol, }; static void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev) @@ -529,11 +533,13 @@ err: return ret; } -int ipvlan_link_new(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); struct ipvl_dev *ipvlan = netdev_priv(dev); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct ipvl_port *port; struct net_device *phy_dev; int err; @@ -542,7 +548,7 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, if (!tb[IFLA_LINK]) return -EINVAL; - phy_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); + phy_dev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK])); if (!phy_dev) return -ENODEV; @@ -599,15 +605,15 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, port->dev_id_start = 0x1; /* Since L2 address is shared among all IPvlan slaves including - * master, use unique 16 bit dev-ids to diffentiate among them. + * master, use unique 16 bit dev-ids to differentiate among them. * Assign IDs between 0x1 and 0xFFFE (used by the master) to each * slave link [see addrconf_ifid_eui48()]. */ - err = ida_simple_get(&port->ida, port->dev_id_start, 0xFFFE, - GFP_KERNEL); + err = ida_alloc_range(&port->ida, port->dev_id_start, 0xFFFD, + GFP_KERNEL); if (err < 0) - err = ida_simple_get(&port->ida, 0x1, port->dev_id_start, - GFP_KERNEL); + err = ida_alloc_range(&port->ida, 0x1, port->dev_id_start - 1, + GFP_KERNEL); if (err < 0) goto unregister_netdev; dev->dev_id = err; @@ -639,7 +645,7 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, unlink_netdev: netdev_upper_dev_unlink(phy_dev, dev); remove_ida: - ida_simple_remove(&port->ida, dev->dev_id); + ida_free(&port->ida, dev->dev_id); unregister_netdev: unregister_netdevice(dev); return err; @@ -659,7 +665,7 @@ void ipvlan_link_delete(struct net_device *dev, struct list_head *head) } spin_unlock_bh(&ipvlan->addrs_lock); - ida_simple_remove(&ipvlan->port->ida, dev->dev_id); + ida_free(&ipvlan->port->ida, dev->dev_id); list_del_rcu(&ipvlan->pnode); unregister_netdevice_queue(dev, head); netdev_upper_dev_unlink(ipvlan->phy_dev, dev); @@ -733,6 +739,7 @@ static int ipvlan_device_event(struct notifier_block *unused, switch (event) { case NETDEV_UP: + case NETDEV_DOWN: case NETDEV_CHANGE: list_for_each_entry(ipvlan, &port->ipvlans, pnode) netif_stacked_transfer_operstate(ipvlan->phy_dev, @@ -748,7 +755,8 @@ static int ipvlan_device_event(struct notifier_block *unused, write_pnet(&port->pnet, newnet); - ipvlan_migrate_l3s_hook(oldnet, newnet); + if (port->mode == IPVLAN_MODE_L3S) + ipvlan_migrate_l3s_hook(oldnet, newnet); break; } case NETDEV_UNREGISTER: @@ -776,9 +784,9 @@ static int ipvlan_device_event(struct notifier_block *unused, case NETDEV_PRE_CHANGEADDR: prechaddr_info = ptr; list_for_each_entry(ipvlan, &port->ipvlans, pnode) { - err = dev_pre_changeaddr_notify(ipvlan->dev, - prechaddr_info->dev_addr, - extack); + err = netif_pre_changeaddr_notify(ipvlan->dev, + prechaddr_info->dev_addr, + extack); if (err) return notifier_from_errno(err); } @@ -794,6 +802,12 @@ static int ipvlan_device_event(struct notifier_block *unused, case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; + + case NETDEV_NOTIFY_PEERS: + case NETDEV_BONDING_FAILOVER: + case NETDEV_RESEND_IGMP: + list_for_each_entry(ipvlan, &port->ipvlans, pnode) + call_netdevice_notifiers(event, ipvlan->dev); } return NOTIFY_DONE; } @@ -1080,3 +1094,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Mahesh Bandewar <maheshb@google.com>"); MODULE_DESCRIPTION("Driver for L3 (IPv6/IPv4) based VLANs"); MODULE_ALIAS_RTNL_LINK("ipvlan"); +MODULE_IMPORT_NS("NETDEV_INTERNAL"); diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c index dde272586e80..edd13916831a 100644 --- a/drivers/net/ipvlan/ipvtap.c +++ b/drivers/net/ipvlan/ipvtap.c @@ -38,7 +38,6 @@ static const void *ipvtap_net_namespace(const struct device *d) static struct class ipvtap_class = { .name = "ipvtap", - .owner = THIS_MODULE, .ns_type = &net_ns_type_operations, .namespace = ipvtap_net_namespace, }; @@ -74,8 +73,8 @@ static void ipvtap_update_features(struct tap_dev *tap, netdev_update_features(vlan->dev); } -static int ipvtap_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int ipvtap_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct ipvtap_dev *vlantap = netdev_priv(dev); @@ -98,7 +97,7 @@ static int ipvtap_newlink(struct net *src_net, struct net_device *dev, /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ - err = ipvlan_link_new(src_net, dev, tb, data, extack); + err = ipvlan_link_new(dev, params, extack); if (err) { netdev_rx_handler_unregister(dev); return err; @@ -238,4 +237,5 @@ static void __exit ipvtap_exit(void) module_exit(ipvtap_exit); MODULE_ALIAS_RTNL_LINK("ipvtap"); MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>"); +MODULE_DESCRIPTION("IP-VLAN based tap driver"); MODULE_LICENSE("GPL"); |
