aboutsummaryrefslogtreecommitdiff
path: root/drivers/net/vxlan.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/vxlan.c')
-rw-r--r--drivers/net/vxlan.c732
1 files changed, 505 insertions, 227 deletions
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index bf64b4191dc..9f79192c9aa 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -40,6 +40,7 @@
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/vxlan.h>
+#include <net/protocol.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/addrconf.h>
@@ -60,10 +61,6 @@
#define VXLAN_N_VID (1u << 24)
#define VXLAN_VID_MASK (VXLAN_N_VID - 1)
-/* IP header + UDP + VXLAN + Ethernet header */
-#define VXLAN_HEADROOM (20 + 8 + 8 + 14)
-/* IPv6 header + UDP + VXLAN + Ethernet header */
-#define VXLAN6_HEADROOM (40 + 8 + 8 + 14)
#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
#define VXLAN_FLAGS 0x08000000 /* struct vxlanhdr.vx_flags required value. */
@@ -130,6 +127,7 @@ struct vxlan_dev {
struct list_head next; /* vxlan's per namespace list */
struct vxlan_sock *vn_sock; /* listening socket */
struct net_device *dev;
+ struct net *net; /* netns for packet i/o */
struct vxlan_rdst default_dst; /* default destination */
union vxlan_addr saddr; /* source address */
__be16 dst_port;
@@ -137,7 +135,7 @@ struct vxlan_dev {
__u16 port_max;
__u8 tos; /* TOS override */
__u8 ttl;
- u32 flags; /* VXLAN_F_* below */
+ u32 flags; /* VXLAN_F_* in vxlan.h */
struct work_struct sock_work;
struct work_struct igmp_join;
@@ -152,13 +150,6 @@ struct vxlan_dev {
struct hlist_head fdb_head[FDB_HASH_SIZE];
};
-#define VXLAN_F_LEARN 0x01
-#define VXLAN_F_PROXY 0x02
-#define VXLAN_F_RSC 0x04
-#define VXLAN_F_L2MISS 0x08
-#define VXLAN_F_L3MISS 0x10
-#define VXLAN_F_IPV6 0x20 /* internal flag */
-
/* salt for hash table */
static u32 vxlan_salt __read_mostly;
static struct workqueue_struct *vxlan_wq;
@@ -348,7 +339,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
ndm->ndm_state = fdb->state;
ndm->ndm_ifindex = vxlan->dev->ifindex;
ndm->ndm_flags = fdb->flags;
- ndm->ndm_type = NDA_DST;
+ ndm->ndm_type = RTN_UNICAST;
if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
goto nla_put_failure;
@@ -392,8 +383,8 @@ static inline size_t vxlan_nlmsg_size(void)
+ nla_total_size(sizeof(struct nda_cacheinfo));
}
-static void vxlan_fdb_notify(struct vxlan_dev *vxlan,
- struct vxlan_fdb *fdb, int type)
+static void vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb,
+ struct vxlan_rdst *rd, int type)
{
struct net *net = dev_net(vxlan->dev);
struct sk_buff *skb;
@@ -403,8 +394,7 @@ static void vxlan_fdb_notify(struct vxlan_dev *vxlan,
if (skb == NULL)
goto errout;
- err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0,
- first_remote_rtnl(fdb));
+ err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0, rd);
if (err < 0) {
/* -EMSGSIZE implies BUG in vxlan_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
@@ -430,10 +420,7 @@ static void vxlan_ip_miss(struct net_device *dev, union vxlan_addr *ipa)
.remote_vni = VXLAN_N_VID,
};
- INIT_LIST_HEAD(&f.remotes);
- list_add_rcu(&remote.list, &f.remotes);
-
- vxlan_fdb_notify(vxlan, &f, RTM_GETNEIGH);
+ vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH);
}
static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN])
@@ -441,11 +428,11 @@ static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN])
struct vxlan_fdb f = {
.state = NUD_STALE,
};
+ struct vxlan_rdst remote = { };
- INIT_LIST_HEAD(&f.remotes);
memcpy(f.eth_addr, eth_addr, ETH_ALEN);
- vxlan_fdb_notify(vxlan, &f, RTM_GETNEIGH);
+ vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH);
}
/* Hash Ethernet address */
@@ -472,7 +459,6 @@ static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan,
/* Look up Ethernet address in forwarding table */
static struct vxlan_fdb *__vxlan_find_mac(struct vxlan_dev *vxlan,
const u8 *mac)
-
{
struct hlist_head *head = vxlan_fdb_head(vxlan, mac);
struct vxlan_fdb *f;
@@ -537,7 +523,8 @@ static int vxlan_fdb_replace(struct vxlan_fdb *f,
/* Add/update destinations for multicast */
static int vxlan_fdb_append(struct vxlan_fdb *f,
- union vxlan_addr *ip, __be16 port, __u32 vni, __u32 ifindex)
+ union vxlan_addr *ip, __be16 port, __u32 vni,
+ __u32 ifindex, struct vxlan_rdst **rdp)
{
struct vxlan_rdst *rd;
@@ -555,16 +542,110 @@ static int vxlan_fdb_append(struct vxlan_fdb *f,
list_add_tail_rcu(&rd->list, &f->remotes);
+ *rdp = rd;
return 1;
}
+static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+{
+ struct sk_buff *p, **pp = NULL;
+ struct vxlanhdr *vh, *vh2;
+ struct ethhdr *eh, *eh2;
+ unsigned int hlen, off_vx, off_eth;
+ const struct packet_offload *ptype;
+ __be16 type;
+ int flush = 1;
+
+ off_vx = skb_gro_offset(skb);
+ hlen = off_vx + sizeof(*vh);
+ vh = skb_gro_header_fast(skb, off_vx);
+ if (skb_gro_header_hard(skb, hlen)) {
+ vh = skb_gro_header_slow(skb, hlen, off_vx);
+ if (unlikely(!vh))
+ goto out;
+ }
+ skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */
+ skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr));
+
+ off_eth = skb_gro_offset(skb);
+ hlen = off_eth + sizeof(*eh);
+ eh = skb_gro_header_fast(skb, off_eth);
+ if (skb_gro_header_hard(skb, hlen)) {
+ eh = skb_gro_header_slow(skb, hlen, off_eth);
+ if (unlikely(!eh))
+ goto out;
+ }
+
+ flush = 0;
+
+ for (p = *head; p; p = p->next) {
+ if (!NAPI_GRO_CB(p)->same_flow)
+ continue;
+
+ vh2 = (struct vxlanhdr *)(p->data + off_vx);
+ eh2 = (struct ethhdr *)(p->data + off_eth);
+ if (vh->vx_vni != vh2->vx_vni || compare_ether_header(eh, eh2)) {
+ NAPI_GRO_CB(p)->same_flow = 0;
+ continue;
+ }
+ }
+
+ type = eh->h_proto;
+
+ rcu_read_lock();
+ ptype = gro_find_receive_by_type(type);
+ if (ptype == NULL) {
+ flush = 1;
+ goto out_unlock;
+ }
+
+ skb_gro_pull(skb, sizeof(*eh)); /* pull inner eth header */
+ skb_gro_postpull_rcsum(skb, eh, sizeof(*eh));
+ pp = ptype->callbacks.gro_receive(head, skb);
+
+out_unlock:
+ rcu_read_unlock();
+out:
+ NAPI_GRO_CB(skb)->flush |= flush;
+
+ return pp;
+}
+
+static int vxlan_gro_complete(struct sk_buff *skb, int nhoff)
+{
+ struct ethhdr *eh;
+ struct packet_offload *ptype;
+ __be16 type;
+ int vxlan_len = sizeof(struct vxlanhdr) + sizeof(struct ethhdr);
+ int err = -ENOSYS;
+
+ eh = (struct ethhdr *)(skb->data + nhoff + sizeof(struct vxlanhdr));
+ type = eh->h_proto;
+
+ rcu_read_lock();
+ ptype = gro_find_complete_by_type(type);
+ if (ptype != NULL)
+ err = ptype->callbacks.gro_complete(skb, nhoff + vxlan_len);
+
+ rcu_read_unlock();
+ return err;
+}
+
/* Notify netdevs that UDP port started listening */
-static void vxlan_notify_add_rx_port(struct sock *sk)
+static void vxlan_notify_add_rx_port(struct vxlan_sock *vs)
{
struct net_device *dev;
+ struct sock *sk = vs->sock->sk;
struct net *net = sock_net(sk);
sa_family_t sa_family = sk->sk_family;
- u16 port = htons(inet_sk(sk)->inet_sport);
+ __be16 port = inet_sk(sk)->inet_sport;
+ int err;
+
+ if (sa_family == AF_INET) {
+ err = udp_add_offload(&vs->udp_offloads);
+ if (err)
+ pr_warn("vxlan: udp_add_offload failed with status %d\n", err);
+ }
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
@@ -576,12 +657,13 @@ static void vxlan_notify_add_rx_port(struct sock *sk)
}
/* Notify netdevs that UDP port is no more listening */
-static void vxlan_notify_del_rx_port(struct sock *sk)
+static void vxlan_notify_del_rx_port(struct vxlan_sock *vs)
{
struct net_device *dev;
+ struct sock *sk = vs->sock->sk;
struct net *net = sock_net(sk);
sa_family_t sa_family = sk->sk_family;
- u16 port = htons(inet_sk(sk)->inet_sport);
+ __be16 port = inet_sk(sk)->inet_sport;
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
@@ -590,6 +672,9 @@ static void vxlan_notify_del_rx_port(struct sock *sk)
port);
}
rcu_read_unlock();
+
+ if (sa_family == AF_INET)
+ udp_del_offload(&vs->udp_offloads);
}
/* Add new entry to forwarding table -- assumes lock held */
@@ -599,6 +684,7 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
__be16 port, __u32 vni, __u32 ifindex,
__u8 ndm_flags)
{
+ struct vxlan_rdst *rd = NULL;
struct vxlan_fdb *f;
int notify = 0;
@@ -635,7 +721,8 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
if ((flags & NLM_F_APPEND) &&
(is_multicast_ether_addr(f->eth_addr) ||
is_zero_ether_addr(f->eth_addr))) {
- int rc = vxlan_fdb_append(f, ip, port, vni, ifindex);
+ int rc = vxlan_fdb_append(f, ip, port, vni, ifindex,
+ &rd);
if (rc < 0)
return rc;
@@ -665,15 +752,18 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
INIT_LIST_HEAD(&f->remotes);
memcpy(f->eth_addr, mac, ETH_ALEN);
- vxlan_fdb_append(f, ip, port, vni, ifindex);
+ vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
++vxlan->addrcnt;
hlist_add_head_rcu(&f->hlist,
vxlan_fdb_head(vxlan, mac));
}
- if (notify)
- vxlan_fdb_notify(vxlan, f, RTM_NEWNEIGH);
+ if (notify) {
+ if (rd == NULL)
+ rd = first_remote_rtnl(f);
+ vxlan_fdb_notify(vxlan, f, rd, RTM_NEWNEIGH);
+ }
return 0;
}
@@ -694,7 +784,7 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
"delete %pM\n", f->eth_addr);
--vxlan->addrcnt;
- vxlan_fdb_notify(vxlan, f, RTM_DELNEIGH);
+ vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
hlist_del_rcu(&f->hlist);
call_rcu(&f->rcu, vxlan_fdb_free);
@@ -745,10 +835,9 @@ static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan,
if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32))
return -EINVAL;
*ifindex = nla_get_u32(tb[NDA_IFINDEX]);
- tdev = dev_get_by_index(net, *ifindex);
+ tdev = __dev_get_by_index(net, *ifindex);
if (!tdev)
return -EADDRNOTAVAIL;
- dev_put(tdev);
} else {
*ifindex = 0;
}
@@ -781,6 +870,9 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
if (err)
return err;
+ if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family)
+ return -EAFNOSUPPORT;
+
spin_lock_bh(&vxlan->hash_lock);
err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
port, vni, ifindex, ndm->ndm_flags);
@@ -826,6 +918,7 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
*/
if (rd && !list_is_singular(&f->remotes)) {
list_del_rcu(&rd->list);
+ vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH);
kfree_rcu(rd, rcu);
goto out;
}
@@ -900,7 +993,7 @@ static bool vxlan_snoop(struct net_device *dev,
rdst->remote_ip = *src_ip;
f->updated = jiffies;
- vxlan_fdb_notify(vxlan, f, RTM_NEWNEIGH);
+ vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH);
} else {
/* learned new entry */
spin_lock(&vxlan->hash_lock);
@@ -920,17 +1013,32 @@ static bool vxlan_snoop(struct net_device *dev,
}
/* See if multicast group is already in use by other ID */
-static bool vxlan_group_used(struct vxlan_net *vn, union vxlan_addr *remote_ip)
+static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev)
{
struct vxlan_dev *vxlan;
+ /* The vxlan_sock is only used by dev, leaving group has
+ * no effect on other vxlan devices.
+ */
+ if (atomic_read(&dev->vn_sock->refcnt) == 1)
+ return false;
+
list_for_each_entry(vxlan, &vn->vxlan_list, next) {
- if (!netif_running(vxlan->dev))
+ if (!netif_running(vxlan->dev) || vxlan == dev)
continue;
- if (vxlan_addr_equal(&vxlan->default_dst.remote_ip,
- remote_ip))
- return true;
+ if (vxlan->vn_sock != dev->vn_sock)
+ continue;
+
+ if (!vxlan_addr_equal(&vxlan->default_dst.remote_ip,
+ &dev->default_dst.remote_ip))
+ continue;
+
+ if (vxlan->default_dst.remote_ifindex !=
+ dev->default_dst.remote_ifindex)
+ continue;
+
+ return true;
}
return false;
@@ -952,9 +1060,8 @@ void vxlan_sock_release(struct vxlan_sock *vs)
spin_lock(&vn->sock_lock);
hlist_del_rcu(&vs->hlist);
- smp_wmb();
- vs->sock->sk->sk_user_data = NULL;
- vxlan_notify_del_rx_port(sk);
+ rcu_assign_sk_user_data(vs->sock->sk, NULL);
+ vxlan_notify_del_rx_port(vs);
spin_unlock(&vn->sock_lock);
queue_work(vxlan_wq, &vs->del_work);
@@ -1028,7 +1135,6 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
struct vxlan_sock *vs;
struct vxlanhdr *vxh;
- __be16 port;
/* Need Vxlan and inner Ethernet header to be present */
if (!pskb_may_pull(skb, VXLAN_HLEN))
@@ -1046,13 +1152,12 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
if (iptunnel_pull_header(skb, VXLAN_HLEN, htons(ETH_P_TEB)))
goto drop;
- port = inet_sk(sk)->inet_sport;
-
- smp_read_barrier_depends();
- vs = (struct vxlan_sock *)sk->sk_user_data;
+ vs = rcu_dereference_sk_user_data(sk);
if (!vs)
goto drop;
+ skb_pop_rcv_encapsulation(skb);
+
vs->rcv(vs, skb, vxh->vx_vni);
return 0;
@@ -1072,7 +1177,7 @@ static void vxlan_rcv(struct vxlan_sock *vs,
struct iphdr *oip = NULL;
struct ipv6hdr *oip6 = NULL;
struct vxlan_dev *vxlan;
- struct pcpu_tstats *stats;
+ struct pcpu_sw_netstats *stats;
union vxlan_addr saddr;
__u32 vni;
int err = 0;
@@ -1086,7 +1191,9 @@ static void vxlan_rcv(struct vxlan_sock *vs,
remote_ip = &vxlan->default_dst.remote_ip;
skb_reset_mac_header(skb);
+ skb_scrub_packet(skb, !net_eq(vxlan->net, dev_net(vxlan->dev)));
skb->protocol = eth_type_trans(skb, vxlan->dev);
+ skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
/* Ignore packet loops (and multicast echo) */
if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr))
@@ -1111,17 +1218,6 @@ static void vxlan_rcv(struct vxlan_sock *vs,
skb_reset_network_header(skb);
- /* If the NIC driver gave us an encapsulated packet with
- * CHECKSUM_UNNECESSARY and Rx checksum feature is enabled,
- * leave the CHECKSUM_UNNECESSARY, the device checksummed it
- * for us. Otherwise force the upper layers to verify it.
- */
- if (skb->ip_summed != CHECKSUM_UNNECESSARY || !skb->encapsulation ||
- !(vxlan->dev->features & NETIF_F_RXCSUM))
- skb->ip_summed = CHECKSUM_NONE;
-
- skb->encapsulation = 0;
-
if (oip6)
err = IP6_ECN_decapsulate(oip6, skb);
if (oip)
@@ -1216,6 +1312,9 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
neigh_release(n);
+ if (reply == NULL)
+ goto out;
+
skb_reset_mac_header(reply);
__skb_pull(reply, skb_network_offset(reply));
reply->ip_summed = CHECKSUM_UNNECESSARY;
@@ -1237,15 +1336,103 @@ out:
}
#if IS_ENABLED(CONFIG_IPV6)
+
+static struct sk_buff *vxlan_na_create(struct sk_buff *request,
+ struct neighbour *n, bool isrouter)
+{
+ struct net_device *dev = request->dev;
+ struct sk_buff *reply;
+ struct nd_msg *ns, *na;
+ struct ipv6hdr *pip6;
+ u8 *daddr;
+ int na_olen = 8; /* opt hdr + ETH_ALEN for target */
+ int ns_olen;
+ int i, len;
+
+ if (dev == NULL)
+ return NULL;
+
+ len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +
+ sizeof(*na) + na_olen + dev->needed_tailroom;
+ reply = alloc_skb(len, GFP_ATOMIC);
+ if (reply == NULL)
+ return NULL;
+
+ reply->protocol = htons(ETH_P_IPV6);
+ reply->dev = dev;
+ skb_reserve(reply, LL_RESERVED_SPACE(request->dev));
+ skb_push(reply, sizeof(struct ethhdr));
+ skb_set_mac_header(reply, 0);
+
+ ns = (struct nd_msg *)skb_transport_header(request);
+
+ daddr = eth_hdr(request)->h_source;
+ ns_olen = request->len - skb_transport_offset(request) - sizeof(*ns);
+ for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) {
+ if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
+ daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
+ break;
+ }
+ }
+
+ /* Ethernet header */
+ ether_addr_copy(eth_hdr(reply)->h_dest, daddr);
+ ether_addr_copy(eth_hdr(reply)->h_source, n->ha);
+ eth_hdr(reply)->h_proto = htons(ETH_P_IPV6);
+ reply->protocol = htons(ETH_P_IPV6);
+
+ skb_pull(reply, sizeof(struct ethhdr));
+ skb_set_network_header(reply, 0);
+ skb_put(reply, sizeof(struct ipv6hdr));
+
+ /* IPv6 header */
+
+ pip6 = ipv6_hdr(reply);
+ memset(pip6, 0, sizeof(struct ipv6hdr));
+ pip6->version = 6;
+ pip6->priority = ipv6_hdr(request)->priority;
+ pip6->nexthdr = IPPROTO_ICMPV6;
+ pip6->hop_limit = 255;
+ pip6->daddr = ipv6_hdr(request)->saddr;
+ pip6->saddr = *(struct in6_addr *)n->primary_key;
+
+ skb_pull(reply, sizeof(struct ipv6hdr));
+ skb_set_transport_header(reply, 0);
+
+ na = (struct nd_msg *)skb_put(reply, sizeof(*na) + na_olen);
+
+ /* Neighbor Advertisement */
+ memset(na, 0, sizeof(*na)+na_olen);
+ na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
+ na->icmph.icmp6_router = isrouter;
+ na->icmph.icmp6_override = 1;
+ na->icmph.icmp6_solicited = 1;
+ na->target = ns->target;
+ ether_addr_copy(&na->opt[2], n->ha);
+ na->opt[0] = ND_OPT_TARGET_LL_ADDR;
+ na->opt[1] = na_olen >> 3;
+
+ na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr,
+ &pip6->daddr, sizeof(*na)+na_olen, IPPROTO_ICMPV6,
+ csum_partial(na, sizeof(*na)+na_olen, 0));
+
+ pip6->payload_len = htons(sizeof(*na)+na_olen);
+
+ skb_push(reply, sizeof(struct ipv6hdr));
+
+ reply->ip_summed = CHECKSUM_UNNECESSARY;
+
+ return reply;
+}
+
static int neigh_reduce(struct net_device *dev, struct sk_buff *skb)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
- struct neighbour *n;
- union vxlan_addr ipa;
+ struct nd_msg *msg;
const struct ipv6hdr *iphdr;
const struct in6_addr *saddr, *daddr;
- struct nd_msg *msg;
- struct inet6_dev *in6_dev = NULL;
+ struct neighbour *n;
+ struct inet6_dev *in6_dev;
in6_dev = __in6_dev_get(dev);
if (!in6_dev)
@@ -1258,19 +1445,20 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb)
saddr = &iphdr->saddr;
daddr = &iphdr->daddr;
- if (ipv6_addr_loopback(daddr) ||
- ipv6_addr_is_multicast(daddr))
- goto out;
-
msg = (struct nd_msg *)skb_transport_header(skb);
if (msg->icmph.icmp6_code != 0 ||
msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
goto out;
- n = neigh_lookup(ipv6_stub->nd_tbl, daddr, dev);
+ if (ipv6_addr_loopback(daddr) ||
+ ipv6_addr_is_multicast(&msg->target))
+ goto out;
+
+ n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev);
if (n) {
struct vxlan_fdb *f;
+ struct sk_buff *reply;
if (!(n->nud_state & NUD_CONNECTED)) {
neigh_release(n);
@@ -1284,13 +1472,23 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb)
goto out;
}
- ipv6_stub->ndisc_send_na(dev, n, saddr, &msg->target,
- !!in6_dev->cnf.forwarding,
- true, false, false);
+ reply = vxlan_na_create(skb, n,
+ !!(f ? f->flags & NTF_ROUTER : 0));
+
neigh_release(n);
+
+ if (reply == NULL)
+ goto out;
+
+ if (netif_rx_ni(reply) == NET_RX_DROP)
+ dev->stats.rx_dropped++;
+
} else if (vxlan->flags & VXLAN_F_L3MISS) {
- ipa.sin6.sin6_addr = *daddr;
- ipa.sa.sa_family = AF_INET6;
+ union vxlan_addr ipa = {
+ .sin6.sin6_addr = msg->target,
+ .sa.sa_family = AF_INET6,
+ };
+
vxlan_ip_miss(dev, &ipa);
}
@@ -1372,20 +1570,6 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
return false;
}
-static void vxlan_sock_put(struct sk_buff *skb)
-{
- sock_put(skb->sk);
-}
-
-/* On transmit, associate with the tunnel socket */
-static void vxlan_set_owner(struct sock *sk, struct sk_buff *skb)
-{
- skb_orphan(skb);
- sock_hold(sk);
- skb->sk = sk;
- skb->destructor = vxlan_sock_put;
-}
-
/* Compute source port for outgoing packet
* first choice to use L4 flow hash since it will spread
* better and maybe available from hardware
@@ -1396,7 +1580,7 @@ __be16 vxlan_src_port(__u16 port_min, __u16 port_max, struct sk_buff *skb)
unsigned int range = (port_max - port_min) + 1;
u32 hash;
- hash = skb_get_rxhash(skb);
+ hash = skb_get_hash(skb);
if (!hash)
hash = jhash(skb->data, 2 * ETH_ALEN,
(__force u32) skb->protocol);
@@ -1405,18 +1589,11 @@ __be16 vxlan_src_port(__u16 port_min, __u16 port_max, struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(vxlan_src_port);
-static int handle_offloads(struct sk_buff *skb)
+static inline struct sk_buff *vxlan_handle_offloads(struct sk_buff *skb,
+ bool udp_csum)
{
- if (skb_is_gso(skb)) {
- int err = skb_unclone(skb, GFP_ATOMIC);
- if (unlikely(err))
- return err;
-
- skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
- } else if (skb->ip_summed != CHECKSUM_PARTIAL)
- skb->ip_summed = CHECKSUM_NONE;
-
- return 0;
+ int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+ return iptunnel_handle_offloads(skb, udp_csum, type);
}
#if IS_ENABLED(CONFIG_IPV6)
@@ -1424,7 +1601,8 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
struct dst_entry *dst, struct sk_buff *skb,
struct net_device *dev, struct in6_addr *saddr,
struct in6_addr *daddr, __u8 prio, __u8 ttl,
- __be16 src_port, __be16 dst_port, __be32 vni)
+ __be16 src_port, __be16 dst_port, __be32 vni,
+ bool xnet)
{
struct ipv6hdr *ip6h;
struct vxlanhdr *vxh;
@@ -1432,12 +1610,11 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
int min_headroom;
int err;
- if (!skb->encapsulation) {
- skb_reset_inner_headers(skb);
- skb->encapsulation = 1;
- }
+ skb = vxlan_handle_offloads(skb, !udp_get_no_check6_tx(vs->sock->sk));
+ if (IS_ERR(skb))
+ return -EINVAL;
- skb_scrub_packet(skb, false);
+ skb_scrub_packet(skb, xnet);
min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len
+ VXLAN_HLEN + sizeof(struct ipv6hdr)
@@ -1469,27 +1646,14 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
uh->source = src_port;
uh->len = htons(skb->len);
- uh->check = 0;
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
IPSKB_REROUTED);
skb_dst_set(skb, dst);
- if (!skb_is_gso(skb) && !(dst->dev->features & NETIF_F_IPV6_CSUM)) {
- __wsum csum = skb_checksum(skb, 0, skb->len, 0);
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- uh->check = csum_ipv6_magic(saddr, daddr, skb->len,
- IPPROTO_UDP, csum);
- if (uh->check == 0)
- uh->check = CSUM_MANGLED_0;
- } else {
- skb->ip_summed = CHECKSUM_PARTIAL;
- skb->csum_start = skb_transport_header(skb) - skb->head;
- skb->csum_offset = offsetof(struct udphdr, check);
- uh->check = ~csum_ipv6_magic(saddr, daddr,
- skb->len, IPPROTO_UDP, 0);
- }
+ udp6_set_csum(udp_get_no_check6_tx(vs->sock->sk), skb,
+ saddr, daddr, skb->len);
__skb_push(skb, sizeof(*ip6h));
skb_reset_network_header(skb);
@@ -1505,12 +1669,6 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
ip6h->daddr = *daddr;
ip6h->saddr = *saddr;
- vxlan_set_owner(vs->sock->sk, skb);
-
- err = handle_offloads(skb);
- if (err)
- return err;
-
ip6tunnel_xmit(skb, dev);
return 0;
}
@@ -1519,17 +1677,16 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
int vxlan_xmit_skb(struct vxlan_sock *vs,
struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
- __be16 src_port, __be16 dst_port, __be32 vni)
+ __be16 src_port, __be16 dst_port, __be32 vni, bool xnet)
{
struct vxlanhdr *vxh;
struct udphdr *uh;
int min_headroom;
int err;
- if (!skb->encapsulation) {
- skb_reset_inner_headers(skb);
- skb->encapsulation = 1;
- }
+ skb = vxlan_handle_offloads(skb, !vs->sock->sk->sk_no_check_tx);
+ if (IS_ERR(skb))
+ return -EINVAL;
min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
+ VXLAN_HLEN + sizeof(struct iphdr)
@@ -1561,16 +1718,12 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
uh->source = src_port;
uh->len = htons(skb->len);
- uh->check = 0;
- vxlan_set_owner(vs->sock->sk, skb);
+ udp_set_csum(vs->sock->sk->sk_no_check_tx, skb,
+ src, dst, skb->len);
- err = handle_offloads(skb);
- if (err)
- return err;
-
- return iptunnel_xmit(rt, skb, src, dst, IPPROTO_UDP, tos, ttl, df,
- false);
+ return iptunnel_xmit(vs->sock->sk, rt, skb, src, dst, IPPROTO_UDP,
+ tos, ttl, df, xnet);
}
EXPORT_SYMBOL_GPL(vxlan_xmit_skb);
@@ -1578,11 +1731,12 @@ EXPORT_SYMBOL_GPL(vxlan_xmit_skb);
static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
struct vxlan_dev *dst_vxlan)
{
- struct pcpu_tstats *tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
- struct pcpu_tstats *rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats);
+ struct pcpu_sw_netstats *tx_stats, *rx_stats;
union vxlan_addr loopback;
union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip;
+ tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
+ rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats);
skb->pkt_type = PACKET_HOST;
skb->encapsulation = 0;
skb->dev = dst_vxlan->dev;
@@ -1662,7 +1816,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
fl4.daddr = dst->sin.sin_addr.s_addr;
fl4.saddr = vxlan->saddr.sin.sin_addr.s_addr;
- rt = ip_route_output_key(dev_net(dev), &fl4);
+ rt = ip_route_output_key(vxlan->net, &fl4);
if (IS_ERR(rt)) {
netdev_dbg(dev, "no route to %pI4\n",
&dst->sin.sin_addr.s_addr);
@@ -1674,7 +1828,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
netdev_dbg(dev, "circular route to %pI4\n",
&dst->sin.sin_addr.s_addr);
dev->stats.collisions++;
- goto tx_error;
+ goto rt_tx_error;
}
/* Bypass encapsulation if the destination is local */
@@ -1683,7 +1837,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
struct vxlan_dev *dst_vxlan;
ip_rt_put(rt);
- dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port);
+ dst_vxlan = vxlan_find_vni(vxlan->net, vni, dst_port);
if (!dst_vxlan)
goto tx_error;
vxlan_encap_bypass(skb, vxlan, dst_vxlan);
@@ -1696,7 +1850,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
err = vxlan_xmit_skb(vxlan->vn_sock, rt, skb,
fl4.saddr, dst->sin.sin_addr.s_addr,
tos, ttl, df, src_port, dst_port,
- htonl(vni << 8));
+ htonl(vni << 8),
+ !net_eq(vxlan->net, dev_net(vxlan->dev)));
if (err < 0)
goto rt_tx_error;
@@ -1736,7 +1891,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
struct vxlan_dev *dst_vxlan;
dst_release(ndst);
- dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port);
+ dst_vxlan = vxlan_find_vni(vxlan->net, vni, dst_port);
if (!dst_vxlan)
goto tx_error;
vxlan_encap_bypass(skb, vxlan, dst_vxlan);
@@ -1747,7 +1902,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
err = vxlan6_xmit_skb(vxlan->vn_sock, ndst, skb,
dev, &fl6.saddr, &fl6.daddr, 0, ttl,
- src_port, dst_port, htonl(vni << 8));
+ src_port, dst_port, htonl(vni << 8),
+ !net_eq(vxlan->net, dev_net(vxlan->dev)));
#endif
}
@@ -1776,7 +1932,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
struct vxlan_dev *vxlan = netdev_priv(dev);
struct ethhdr *eth;
bool did_rsc = false;
- struct vxlan_rdst *rdst;
+ struct vxlan_rdst *rdst, *fdst = NULL;
struct vxlan_fdb *f;
skb_reset_mac_header(skb);
@@ -1818,7 +1974,7 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
vxlan_fdb_miss(vxlan, eth->h_dest);
dev->stats.tx_dropped++;
- dev_kfree_skb(skb);
+ kfree_skb(skb);
return NETDEV_TX_OK;
}
}
@@ -1826,12 +1982,19 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
list_for_each_entry_rcu(rdst, &f->remotes, list) {
struct sk_buff *skb1;
+ if (!fdst) {
+ fdst = rdst;
+ continue;
+ }
skb1 = skb_clone(skb, GFP_ATOMIC);
if (skb1)
vxlan_xmit_one(skb1, dev, rdst, did_rsc);
}
- dev_kfree_skb(skb);
+ if (fdst)
+ vxlan_xmit_one(skb, dev, fdst, did_rsc);
+ else
+ kfree_skb(skb);
return NETDEV_TX_OK;
}
@@ -1884,15 +2047,15 @@ static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan)
static int vxlan_init(struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
- struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
+ struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
struct vxlan_sock *vs;
- dev->tstats = alloc_percpu(struct pcpu_tstats);
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
spin_lock(&vn->sock_lock);
- vs = vxlan_find_sock(dev_net(dev), vxlan->dst_port);
+ vs = vxlan_find_sock(vxlan->net, vxlan->dst_port);
if (vs) {
/* If we have a socket with same port already, reuse it */
atomic_inc(&vs->refcnt);
@@ -1933,7 +2096,6 @@ static void vxlan_uninit(struct net_device *dev)
/* Start ageing timer and join group when device is brought up */
static int vxlan_open(struct net_device *dev)
{
- struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_sock *vs = vxlan->vn_sock;
@@ -1941,8 +2103,7 @@ static int vxlan_open(struct net_device *dev)
if (!vs)
return -ENOTCONN;
- if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip) &&
- vxlan_group_used(vn, &vxlan->default_dst.remote_ip)) {
+ if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip)) {
vxlan_sock_hold(vs);
dev_hold(dev);
queue_work(vxlan_wq, &vxlan->igmp_join);
@@ -1976,12 +2137,12 @@ static void vxlan_flush(struct vxlan_dev *vxlan)
/* Cleanup timer and forwarding table on shutdown */
static int vxlan_stop(struct net_device *dev)
{
- struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
struct vxlan_dev *vxlan = netdev_priv(dev);
+ struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
struct vxlan_sock *vs = vxlan->vn_sock;
if (vs && vxlan_addr_multicast(&vxlan->default_dst.remote_ip) &&
- ! vxlan_group_used(vn, &vxlan->default_dst.remote_ip)) {
+ !vxlan_group_used(vn, vxlan)) {
vxlan_sock_hold(vs);
dev_hold(dev);
queue_work(vxlan_wq, &vxlan->igmp_leave);
@@ -1999,6 +2160,29 @@ static void vxlan_set_multicast_list(struct net_device *dev)
{
}
+static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
+{
+ struct vxlan_dev *vxlan = netdev_priv(dev);
+ struct vxlan_rdst *dst = &vxlan->default_dst;
+ struct net_device *lowerdev;
+ int max_mtu;
+
+ lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex);
+ if (lowerdev == NULL)
+ return eth_change_mtu(dev, new_mtu);
+
+ if (dst->remote_ip.sa.sa_family == AF_INET6)
+ max_mtu = lowerdev->mtu - VXLAN6_HEADROOM;
+ else
+ max_mtu = lowerdev->mtu - VXLAN_HEADROOM;
+
+ if (new_mtu < 68 || new_mtu > max_mtu)
+ return -EINVAL;
+
+ dev->mtu = new_mtu;
+ return 0;
+}
+
static const struct net_device_ops vxlan_netdev_ops = {
.ndo_init = vxlan_init,
.ndo_uninit = vxlan_uninit,
@@ -2007,7 +2191,7 @@ static const struct net_device_ops vxlan_netdev_ops = {
.ndo_start_xmit = vxlan_xmit,
.ndo_get_stats64 = ip_tunnel_get_stats64,
.ndo_set_rx_mode = vxlan_set_multicast_list,
- .ndo_change_mtu = eth_change_mtu,
+ .ndo_change_mtu = vxlan_change_mtu,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = eth_mac_addr,
.ndo_fdb_add = vxlan_fdb_add,
@@ -2021,7 +2205,8 @@ static struct device_type vxlan_type = {
};
/* Calls the ndo_add_vxlan_port of the caller in order to
- * supply the listening VXLAN udp ports.
+ * supply the listening VXLAN udp ports. Callers are expected
+ * to implement the ndo_add_vxlan_port.
*/
void vxlan_get_rx_port(struct net_device *dev)
{
@@ -2029,16 +2214,13 @@ void vxlan_get_rx_port(struct net_device *dev)
struct net *net = dev_net(dev);
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
sa_family_t sa_family;
- u16 port;
- int i;
-
- if (!dev || !dev->netdev_ops || !dev->netdev_ops->ndo_add_vxlan_port)
- return;
+ __be16 port;
+ unsigned int i;
spin_lock(&vn->sock_lock);
for (i = 0; i < PORT_HASH_SIZE; ++i) {
- hlist_for_each_entry_rcu(vs, vs_head(net, i), hlist) {
- port = htons(inet_sk(vs->sock->sk)->inet_sport);
+ hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist) {
+ port = inet_sk(vs->sock->sk)->inet_sport;
sa_family = vs->sock->sk->sk_family;
dev->netdev_ops->ndo_add_vxlan_port(dev, sa_family,
port);
@@ -2058,9 +2240,9 @@ static void vxlan_setup(struct net_device *dev)
eth_hw_addr_random(dev);
ether_setup(dev);
if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6)
- dev->hard_header_len = ETH_HLEN + VXLAN6_HEADROOM;
+ dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM;
else
- dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
+ dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM;
dev->netdev_ops = &vxlan_netdev_ops;
dev->destructor = free_netdev;
@@ -2068,7 +2250,6 @@ static void vxlan_setup(struct net_device *dev)
dev->tx_queue_len = 0;
dev->features |= NETIF_F_LLTX;
- dev->features |= NETIF_F_NETNS_LOCAL;
dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM;
dev->features |= NETIF_F_RXCSUM;
dev->features |= NETIF_F_GSO_SOFTWARE;
@@ -2091,7 +2272,7 @@ static void vxlan_setup(struct net_device *dev)
vxlan->age_timer.function = vxlan_cleanup;
vxlan->age_timer.data = (unsigned long) vxlan;
- inet_get_local_port_range(&low, &high);
+ inet_get_local_port_range(dev_net(dev), &low, &high);
vxlan->port_min = low;
vxlan->port_max = high;
vxlan->dst_port = htons(vxlan_port);
@@ -2184,7 +2365,7 @@ static void vxlan_del_work(struct work_struct *work)
* could be used for both IPv4 and IPv6 communications, but
* users may set bindv6only=1.
*/
-static int create_v6_sock(struct net *net, __be16 port, struct socket **psock)
+static struct socket *create_v6_sock(struct net *net, __be16 port, u32 flags)
{
struct sock *sk;
struct socket *sock;
@@ -2197,7 +2378,7 @@ static int create_v6_sock(struct net *net, __be16 port, struct socket **psock)
rc = sock_create_kern(AF_INET6, SOCK_DGRAM, IPPROTO_UDP, &sock);
if (rc < 0) {
pr_debug("UDPv6 socket create failed\n");
- return rc;
+ return ERR_PTR(rc);
}
/* Put in proper namespace */
@@ -2212,28 +2393,34 @@ static int create_v6_sock(struct net *net, __be16 port, struct socket **psock)
pr_debug("bind for UDPv6 socket %pI6:%u (%d)\n",
&vxlan_addr.sin6_addr, ntohs(vxlan_addr.sin6_port), rc);
sk_release_kernel(sk);
- return rc;
+ return ERR_PTR(rc);
}
/* At this point, IPv6 module should have been loaded in
* sock_create_kern().
*/
BUG_ON(!ipv6_stub);
- *psock = sock;
/* Disable multicast loopback */
inet_sk(sk)->mc_loop = 0;
- return 0;
+
+ if (flags & VXLAN_F_UDP_ZERO_CSUM6_TX)
+ udp_set_no_check6_tx(sk, true);
+
+ if (flags & VXLAN_F_UDP_ZERO_CSUM6_RX)
+ udp_set_no_check6_rx(sk, true);
+
+ return sock;
}
#else
-static int create_v6_sock(struct net *net, __be16 port, struct socket **psock)
+static struct socket *create_v6_sock(struct net *net, __be16 port, u32 flags)
{
- return -EPFNOSUPPORT;
+ return ERR_PTR(-EPFNOSUPPORT);
}
#endif
-static int create_v4_sock(struct net *net, __be16 port, struct socket **psock)
+static struct socket *create_v4_sock(struct net *net, __be16 port, u32 flags)
{
struct sock *sk;
struct socket *sock;
@@ -2248,7 +2435,7 @@ static int create_v4_sock(struct net *net, __be16 port, struct socket **psock)
rc = sock_create_kern(AF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
if (rc < 0) {
pr_debug("UDP socket create failed\n");
- return rc;
+ return ERR_PTR(rc);
}
/* Put in proper namespace */
@@ -2261,27 +2448,31 @@ static int create_v4_sock(struct net *net, __be16 port, struct socket **psock)
pr_debug("bind for UDP socket %pI4:%u (%d)\n",
&vxlan_addr.sin_addr, ntohs(vxlan_addr.sin_port), rc);
sk_release_kernel(sk);
- return rc;
+ return ERR_PTR(rc);
}
- *psock = sock;
/* Disable multicast loopback */
inet_sk(sk)->mc_loop = 0;
- return 0;
+
+ if (!(flags & VXLAN_F_UDP_CSUM))
+ sock->sk->sk_no_check_tx = 1;
+
+ return sock;
}
/* Create new listen socket if needed */
static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
- vxlan_rcv_t *rcv, void *data, bool ipv6)
+ vxlan_rcv_t *rcv, void *data,
+ u32 flags)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
struct vxlan_sock *vs;
struct socket *sock;
struct sock *sk;
- int rc = 0;
unsigned int h;
+ bool ipv6 = !!(flags & VXLAN_F_IPV6);
- vs = kmalloc(sizeof(*vs), GFP_KERNEL);
+ vs = kzalloc(sizeof(*vs), GFP_KERNEL);
if (!vs)
return ERR_PTR(-ENOMEM);
@@ -2291,12 +2482,12 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
INIT_WORK(&vs->del_work, vxlan_del_work);
if (ipv6)
- rc = create_v6_sock(net, port, &sock);
+ sock = create_v6_sock(net, port, flags);
else
- rc = create_v4_sock(net, port, &sock);
- if (rc < 0) {
+ sock = create_v4_sock(net, port, flags);
+ if (IS_ERR(sock)) {
kfree(vs);
- return ERR_PTR(rc);
+ return ERR_CAST(sock);
}
vs->sock = sock;
@@ -2304,12 +2495,16 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
atomic_set(&vs->refcnt, 1);
vs->rcv = rcv;
vs->data = data;
- smp_wmb();
- vs->sock->sk->sk_user_data = vs;
+ rcu_assign_sk_user_data(vs->sock->sk, vs);
+
+ /* Initialize the vxlan udp offloads structure */
+ vs->udp_offloads.port = port;
+ vs->udp_offloads.callbacks.gro_receive = vxlan_gro_receive;
+ vs->udp_offloads.callbacks.gro_complete = vxlan_gro_complete;
spin_lock(&vn->sock_lock);
hlist_add_head_rcu(&vs->hlist, vs_head(net, port));
- vxlan_notify_add_rx_port(sk);
+ vxlan_notify_add_rx_port(vs);
spin_unlock(&vn->sock_lock);
/* Mark socket as an encapsulation socket. */
@@ -2327,12 +2522,12 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
vxlan_rcv_t *rcv, void *data,
- bool no_share, bool ipv6)
+ bool no_share, u32 flags)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
struct vxlan_sock *vs;
- vs = vxlan_socket_create(net, port, rcv, data, ipv6);
+ vs = vxlan_socket_create(net, port, rcv, data, flags);
if (!IS_ERR(vs))
return vs;
@@ -2360,12 +2555,12 @@ EXPORT_SYMBOL_GPL(vxlan_sock_add);
static void vxlan_sock_work(struct work_struct *work)
{
struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, sock_work);
- struct net *net = dev_net(vxlan->dev);
+ struct net *net = vxlan->net;
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
__be16 port = vxlan->dst_port;
struct vxlan_sock *nvs;
- nvs = vxlan_sock_add(net, port, vxlan_rcv, NULL, false, vxlan->flags & VXLAN_F_IPV6);
+ nvs = vxlan_sock_add(net, port, vxlan_rcv, NULL, false, vxlan->flags);
spin_lock(&vn->sock_lock);
if (!IS_ERR(nvs))
vxlan_vs_add_dev(nvs, vxlan);
@@ -2387,12 +2582,15 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
if (!data[IFLA_VXLAN_ID])
return -EINVAL;
+ vxlan->net = dev_net(dev);
+
vni = nla_get_u32(data[IFLA_VXLAN_ID]);
dst->remote_vni = vni;
+ /* Unless IPv6 is explicitly requested, assume IPv4 */
+ dst->remote_ip.sa.sa_family = AF_INET;
if (data[IFLA_VXLAN_GROUP]) {
dst->remote_ip.sin.sin_addr.s_addr = nla_get_be32(data[IFLA_VXLAN_GROUP]);
- dst->remote_ip.sa.sa_family = AF_INET;
} else if (data[IFLA_VXLAN_GROUP6]) {
if (!IS_ENABLED(CONFIG_IPV6))
return -EPFNOSUPPORT;
@@ -2441,10 +2639,10 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
if (!tb[IFLA_MTU])
dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
- /* update header length based on lower device */
- dev->hard_header_len = lowerdev->hard_header_len +
+ dev->needed_headroom = lowerdev->hard_header_len +
(use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
- }
+ } else if (use_ipv6)
+ vxlan->flags |= VXLAN_F_IPV6;
if (data[IFLA_VXLAN_TOS])
vxlan->tos = nla_get_u8(data[IFLA_VXLAN_TOS]);
@@ -2485,22 +2683,37 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
if (data[IFLA_VXLAN_PORT])
vxlan->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]);
+ if (data[IFLA_VXLAN_UDP_CSUM] && nla_get_u8(data[IFLA_VXLAN_UDP_CSUM]))
+ vxlan->flags |= VXLAN_F_UDP_CSUM;
+
+ if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX] &&
+ nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]))
+ vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_TX;
+
+ if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX] &&
+ nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]))
+ vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_RX;
+
if (vxlan_find_vni(net, vni, vxlan->dst_port)) {
pr_info("duplicate VNI %u\n", vni);
return -EEXIST;
}
- SET_ETHTOOL_OPS(dev, &vxlan_ethtool_ops);
+ dev->ethtool_ops = &vxlan_ethtool_ops;
- /* create an fdb entry for default destination */
- err = vxlan_fdb_create(vxlan, all_zeros_mac,
- &vxlan->default_dst.remote_ip,
- NUD_REACHABLE|NUD_PERMANENT,
- NLM_F_EXCL|NLM_F_CREATE,
- vxlan->dst_port, vxlan->default_dst.remote_vni,
- vxlan->default_dst.remote_ifindex, NTF_SELF);
- if (err)
- return err;
+ /* create an fdb entry for a valid default destination */
+ if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
+ err = vxlan_fdb_create(vxlan, all_zeros_mac,
+ &vxlan->default_dst.remote_ip,
+ NUD_REACHABLE|NUD_PERMANENT,
+ NLM_F_EXCL|NLM_F_CREATE,
+ vxlan->dst_port,
+ vxlan->default_dst.remote_vni,
+ vxlan->default_dst.remote_ifindex,
+ NTF_SELF);
+ if (err)
+ return err;
+ }
err = register_netdevice(dev);
if (err) {
@@ -2515,8 +2728,8 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
static void vxlan_dellink(struct net_device *dev, struct list_head *head)
{
- struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
struct vxlan_dev *vxlan = netdev_priv(dev);
+ struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
spin_lock(&vn->sock_lock);
if (!hlist_unhashed(&vxlan->hlist))
@@ -2544,7 +2757,10 @@ static size_t vxlan_get_size(const struct net_device *dev)
nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_AGEING */
nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LIMIT */
nla_total_size(sizeof(struct ifla_vxlan_port_range)) +
- nla_total_size(sizeof(__be16))+ /* IFLA_VXLAN_PORT */
+ nla_total_size(sizeof(__be16)) + /* IFLA_VXLAN_PORT */
+ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_CSUM */
+ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_TX */
+ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_RX */
0;
}
@@ -2604,7 +2820,13 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
!!(vxlan->flags & VXLAN_F_L3MISS)) ||
nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->age_interval) ||
nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->addrmax) ||
- nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->dst_port))
+ nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->dst_port) ||
+ nla_put_u8(skb, IFLA_VXLAN_UDP_CSUM,
+ !!(vxlan->flags & VXLAN_F_UDP_CSUM)) ||
+ nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX,
+ !!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) ||
+ nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_RX,
+ !!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_RX)))
goto nla_put_failure;
if (nla_put(skb, IFLA_VXLAN_PORT_RANGE, sizeof(ports), &ports))
@@ -2629,6 +2851,44 @@ static struct rtnl_link_ops vxlan_link_ops __read_mostly = {
.fill_info = vxlan_fill_info,
};
+static void vxlan_handle_lowerdev_unregister(struct vxlan_net *vn,
+ struct net_device *dev)
+{
+ struct vxlan_dev *vxlan, *next;
+ LIST_HEAD(list_kill);
+
+ list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) {
+ struct vxlan_rdst *dst = &vxlan->default_dst;
+
+ /* In case we created vxlan device with carrier
+ * and we loose the carrier due to module unload
+ * we also need to remove vxlan device. In other
+ * cases, it's not necessary and remote_ifindex
+ * is 0 here, so no matches.
+ */
+ if (dst->remote_ifindex == dev->ifindex)
+ vxlan_dellink(vxlan->dev, &list_kill);
+ }
+
+ unregister_netdevice_many(&list_kill);
+}
+
+static int vxlan_lowerdev_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
+
+ if (event == NETDEV_UNREGISTER)
+ vxlan_handle_lowerdev_unregister(vn, dev);
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block vxlan_notifier_block __read_mostly = {
+ .notifier_call = vxlan_lowerdev_event,
+};
+
static __net_init int vxlan_init_net(struct net *net)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
@@ -2643,15 +2903,26 @@ static __net_init int vxlan_init_net(struct net *net)
return 0;
}
-static __net_exit void vxlan_exit_net(struct net *net)
+static void __net_exit vxlan_exit_net(struct net *net)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
- struct vxlan_dev *vxlan;
+ struct vxlan_dev *vxlan, *next;
+ struct net_device *dev, *aux;
LIST_HEAD(list);
rtnl_lock();
- list_for_each_entry(vxlan, &vn->vxlan_list, next)
- unregister_netdevice_queue(vxlan->dev, &list);
+ for_each_netdev_safe(net, dev, aux)
+ if (dev->rtnl_link_ops == &vxlan_link_ops)
+ unregister_netdevice_queue(dev, &list);
+
+ list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) {
+ /* If vxlan->dev is in the same netns, it has already been added
+ * to the list by the previous loop.
+ */
+ if (!net_eq(dev_net(vxlan->dev), net))
+ unregister_netdevice_queue(dev, &list);
+ }
+
unregister_netdevice_many(&list);
rtnl_unlock();
}
@@ -2673,18 +2944,23 @@ static int __init vxlan_init_module(void)
get_random_bytes(&vxlan_salt, sizeof(vxlan_salt));
- rc = register_pernet_device(&vxlan_net_ops);
+ rc = register_pernet_subsys(&vxlan_net_ops);
if (rc)
goto out1;
- rc = rtnl_link_register(&vxlan_link_ops);
+ rc = register_netdevice_notifier(&vxlan_notifier_block);
if (rc)
goto out2;
- return 0;
+ rc = rtnl_link_register(&vxlan_link_ops);
+ if (rc)
+ goto out3;
+ return 0;
+out3:
+ unregister_netdevice_notifier(&vxlan_notifier_block);
out2:
- unregister_pernet_device(&vxlan_net_ops);
+ unregister_pernet_subsys(&vxlan_net_ops);
out1:
destroy_workqueue(vxlan_wq);
return rc;
@@ -2694,13 +2970,15 @@ late_initcall(vxlan_init_module);
static void __exit vxlan_cleanup_module(void)
{
rtnl_link_unregister(&vxlan_link_ops);
+ unregister_netdevice_notifier(&vxlan_notifier_block);
destroy_workqueue(vxlan_wq);
- unregister_pernet_device(&vxlan_net_ops);
- rcu_barrier();
+ unregister_pernet_subsys(&vxlan_net_ops);
+ /* rcu_barrier() is called by netns */
}
module_exit(vxlan_cleanup_module);
MODULE_LICENSE("GPL");
MODULE_VERSION(VXLAN_VERSION);
MODULE_AUTHOR("Stephen Hemminger <stephen@networkplumber.org>");
+MODULE_DESCRIPTION("Driver for VXLAN encapsulated traffic");
MODULE_ALIAS_RTNL_LINK("vxlan");
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-04 11:15:04 +0000