#include <net/netns/generic.h>
#include <net/vxlan.h>
#include <net/protocol.h>
-#include <net/udp_tunnel.h>
+
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/addrconf.h>
#endif
/* Virtual Network hash table head */
-static inline struct hlist_head *vni_head(struct vxlan_sock *vs, u32 id)
+static inline struct hlist_head *vni_head(struct vxlan_sock *vs, __be32 vni)
{
- return &vs->vni_list[hash_32(id, VNI_HASH_BITS)];
+ return &vs->vni_list[hash_32((__force u32)vni, VNI_HASH_BITS)];
}
/* Socket hash table head */
return NULL;
}
-static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, u32 id)
+static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, __be32 vni)
{
struct vxlan_dev *vxlan;
- hlist_for_each_entry_rcu(vxlan, vni_head(vs, id), hlist) {
- if (vxlan->default_dst.remote_vni == id)
+ /* For flow based devices, map all packets to VNI 0 */
+ if (vs->flags & VXLAN_F_COLLECT_METADATA)
+ vni = 0;
+
+ hlist_for_each_entry_rcu(vxlan, vni_head(vs, vni), hlist) {
+ if (vxlan->default_dst.remote_vni == vni)
return vxlan;
}
}
/* Look up VNI in a per net namespace table */
-static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id,
+static struct vxlan_dev *vxlan_find_vni(struct net *net, __be32 vni,
sa_family_t family, __be16 port,
u32 flags)
{
if (!vs)
return NULL;
- return vxlan_vs_find_vni(vs, id);
+ return vxlan_vs_find_vni(vs, vni);
}
/* Fill in neighbour message in skbuff. */
nla_put_be16(skb, NDA_PORT, rdst->remote_port))
goto nla_put_failure;
if (rdst->remote_vni != vxlan->default_dst.remote_vni &&
- nla_put_u32(skb, NDA_VNI, rdst->remote_vni))
+ nla_put_u32(skb, NDA_VNI, be32_to_cpu(rdst->remote_vni)))
goto nla_put_failure;
if (rdst->remote_ifindex &&
nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex))
};
struct vxlan_rdst remote = {
.remote_ip = *ipa, /* goes to NDA_DST */
- .remote_vni = VXLAN_N_VID,
+ .remote_vni = cpu_to_be32(VXLAN_N_VID),
};
vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH);
/* caller should hold vxlan->hash_lock */
static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f,
union vxlan_addr *ip, __be16 port,
- __u32 vni, __u32 ifindex)
+ __be32 vni, __u32 ifindex)
{
struct vxlan_rdst *rd;
/* Replace destination of unicast mac */
static int vxlan_fdb_replace(struct vxlan_fdb *f,
- union vxlan_addr *ip, __be16 port, __u32 vni, __u32 ifindex)
+ union vxlan_addr *ip, __be16 port, __be32 vni,
+ __u32 ifindex)
{
struct vxlan_rdst *rd;
rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list);
if (!rd)
return 0;
+
+ dst_cache_reset(&rd->dst_cache);
rd->remote_ip = *ip;
rd->remote_port = port;
rd->remote_vni = vni;
/* Add/update destinations for multicast */
static int vxlan_fdb_append(struct vxlan_fdb *f,
- union vxlan_addr *ip, __be16 port, __u32 vni,
+ union vxlan_addr *ip, __be16 port, __be32 vni,
__u32 ifindex, struct vxlan_rdst **rdp)
{
struct vxlan_rdst *rd;
rd = kmalloc(sizeof(*rd), GFP_ATOMIC);
if (rd == NULL)
return -ENOBUFS;
+
+ if (dst_cache_init(&rd->dst_cache, GFP_ATOMIC)) {
+ kfree(rd);
+ return -ENOBUFS;
+ }
+
rd->remote_ip = *ip;
rd->remote_port = port;
rd->remote_vni = vni;
static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb,
unsigned int off,
struct vxlanhdr *vh, size_t hdrlen,
- u32 data, struct gro_remcsum *grc,
+ __be32 vni_field,
+ struct gro_remcsum *grc,
bool nopartial)
{
size_t start, offset;
if (!NAPI_GRO_CB(skb)->csum_valid)
return NULL;
- start = (data & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT;
- offset = start + ((data & VXLAN_RCO_UDP) ?
- offsetof(struct udphdr, check) :
- offsetof(struct tcphdr, check));
+ start = vxlan_rco_start(vni_field);
+ offset = start + vxlan_rco_offset(vni_field);
vh = skb_gro_remcsum_process(skb, (void *)vh, off, hdrlen,
start, offset, grc, nopartial);
int flush = 1;
struct vxlan_sock *vs = container_of(uoff, struct vxlan_sock,
udp_offloads);
- u32 flags;
+ __be32 flags;
struct gro_remcsum grc;
skb_gro_remcsum_init(&grc);
skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr));
- flags = ntohl(vh->vx_flags);
+ flags = vh->vx_flags;
if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) {
vh = vxlan_gro_remcsum(skb, off_vx, vh, sizeof(struct vxlanhdr),
- ntohl(vh->vx_vni), &grc,
+ vh->vx_vni, &grc,
!!(vs->flags &
VXLAN_F_REMCSUM_NOPARTIAL));
skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */
- flush = 0;
-
for (p = *head; p; p = p->next) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
}
pp = eth_gro_receive(head, skb);
+ flush = 0;
out:
skb_gro_remcsum_cleanup(skb, &grc);
static int vxlan_fdb_create(struct vxlan_dev *vxlan,
const u8 *mac, union vxlan_addr *ip,
__u16 state, __u16 flags,
- __be16 port, __u32 vni, __u32 ifindex,
+ __be16 port, __be32 vni, __u32 ifindex,
__u8 ndm_flags)
{
struct vxlan_rdst *rd = NULL;
struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu);
struct vxlan_rdst *rd, *nd;
- list_for_each_entry_safe(rd, nd, &f->remotes, list)
+ list_for_each_entry_safe(rd, nd, &f->remotes, list) {
+ dst_cache_destroy(&rd->dst_cache);
kfree(rd);
+ }
kfree(f);
}
}
static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan,
- union vxlan_addr *ip, __be16 *port, u32 *vni, u32 *ifindex)
+ union vxlan_addr *ip, __be16 *port, __be32 *vni,
+ u32 *ifindex)
{
struct net *net = dev_net(vxlan->dev);
int err;
if (tb[NDA_VNI]) {
if (nla_len(tb[NDA_VNI]) != sizeof(u32))
return -EINVAL;
- *vni = nla_get_u32(tb[NDA_VNI]);
+ *vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI]));
} else {
*vni = vxlan->default_dst.remote_vni;
}
/* struct net *net = dev_net(vxlan->dev); */
union vxlan_addr ip;
__be16 port;
- u32 vni, ifindex;
+ __be32 vni;
+ u32 ifindex;
int err;
if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) {
struct vxlan_rdst *rd = NULL;
union vxlan_addr ip;
__be16 port;
- u32 vni, ifindex;
+ __be32 vni;
+ u32 ifindex;
int err;
err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &vni, &ifindex);
return ret;
}
-static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh,
- size_t hdrlen, u32 data, bool nopartial)
+static bool vxlan_remcsum(struct vxlanhdr *unparsed,
+ struct sk_buff *skb, u32 vxflags)
{
- size_t start, offset, plen;
+ size_t start, offset;
- if (skb->remcsum_offload)
- return vh;
+ if (!(unparsed->vx_flags & VXLAN_HF_RCO) || skb->remcsum_offload)
+ goto out;
- start = (data & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT;
- offset = start + ((data & VXLAN_RCO_UDP) ?
- offsetof(struct udphdr, check) :
- offsetof(struct tcphdr, check));
+ start = vxlan_rco_start(unparsed->vx_vni);
+ offset = start + vxlan_rco_offset(unparsed->vx_vni);
- plen = hdrlen + offset + sizeof(u16);
+ if (!pskb_may_pull(skb, offset + sizeof(u16)))
+ return false;
- if (!pskb_may_pull(skb, plen))
- return NULL;
+ skb_remcsum_process(skb, (void *)(vxlan_hdr(skb) + 1), start, offset,
+ !!(vxflags & VXLAN_F_REMCSUM_NOPARTIAL));
+out:
+ unparsed->vx_flags &= ~VXLAN_HF_RCO;
+ unparsed->vx_vni &= VXLAN_VNI_MASK;
+ return true;
+}
- vh = (struct vxlanhdr *)(udp_hdr(skb) + 1);
+static void vxlan_parse_gbp_hdr(struct vxlanhdr *unparsed,
+ struct sk_buff *skb, u32 vxflags,
+ struct vxlan_metadata *md)
+{
+ struct vxlanhdr_gbp *gbp = (struct vxlanhdr_gbp *)unparsed;
+ struct metadata_dst *tun_dst;
- skb_remcsum_process(skb, (void *)vh + hdrlen, start, offset,
- nopartial);
+ if (!(unparsed->vx_flags & VXLAN_HF_GBP))
+ goto out;
- return vh;
+ md->gbp = ntohs(gbp->policy_id);
+
+ tun_dst = (struct metadata_dst *)skb_dst(skb);
+ if (tun_dst) {
+ tun_dst->u.tun_info.key.tun_flags |= TUNNEL_VXLAN_OPT;
+ tun_dst->u.tun_info.options_len = sizeof(*md);
+ }
+ if (gbp->dont_learn)
+ md->gbp |= VXLAN_GBP_DONT_LEARN;
+
+ if (gbp->policy_applied)
+ md->gbp |= VXLAN_GBP_POLICY_APPLIED;
+
+ /* In flow-based mode, GBP is carried in dst_metadata */
+ if (!(vxflags & VXLAN_F_COLLECT_METADATA))
+ skb->mark = md->gbp;
+out:
+ unparsed->vx_flags &= ~VXLAN_GBP_USED_BITS;
}
-static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
- struct vxlan_metadata *md, u32 vni,
- struct metadata_dst *tun_dst)
+static bool vxlan_set_mac(struct vxlan_dev *vxlan,
+ struct vxlan_sock *vs,
+ struct sk_buff *skb)
{
- struct iphdr *oip = NULL;
- struct ipv6hdr *oip6 = NULL;
- struct vxlan_dev *vxlan;
- struct pcpu_sw_netstats *stats;
union vxlan_addr saddr;
- int err = 0;
-
- /* For flow based devices, map all packets to VNI 0 */
- if (vs->flags & VXLAN_F_COLLECT_METADATA)
- vni = 0;
-
- /* Is this VNI defined? */
- vxlan = vxlan_vs_find_vni(vs, vni);
- if (!vxlan)
- goto drop;
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))
- goto drop;
+ return false;
- /* Get data from the outer IP header */
+ /* Get address from the outer IP header */
if (vxlan_get_sk_family(vs) == AF_INET) {
- oip = ip_hdr(skb);
- saddr.sin.sin_addr.s_addr = oip->saddr;
+ saddr.sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
saddr.sa.sa_family = AF_INET;
#if IS_ENABLED(CONFIG_IPV6)
} else {
- oip6 = ipv6_hdr(skb);
- saddr.sin6.sin6_addr = oip6->saddr;
+ saddr.sin6.sin6_addr = ipv6_hdr(skb)->saddr;
saddr.sa.sa_family = AF_INET6;
#endif
}
- if (tun_dst) {
- skb_dst_set(skb, (struct dst_entry *)tun_dst);
- tun_dst = NULL;
- }
-
if ((vxlan->flags & VXLAN_F_LEARN) &&
vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source))
- goto drop;
-
- skb_reset_network_header(skb);
- /* In flow-based mode, GBP is carried in dst_metadata */
- if (!(vs->flags & VXLAN_F_COLLECT_METADATA))
- skb->mark = md->gbp;
-
- if (oip6)
- err = IP6_ECN_decapsulate(oip6, skb);
- if (oip)
- err = IP_ECN_decapsulate(oip, skb);
-
- if (unlikely(err)) {
- if (log_ecn_error) {
- if (oip6)
- net_info_ratelimited("non-ECT from %pI6\n",
- &oip6->saddr);
- if (oip)
- net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
- &oip->saddr, oip->tos);
- }
- if (err > 1) {
- ++vxlan->dev->stats.rx_frame_errors;
- ++vxlan->dev->stats.rx_errors;
- goto drop;
- }
- }
+ return false;
- stats = this_cpu_ptr(vxlan->dev->tstats);
- u64_stats_update_begin(&stats->syncp);
- stats->rx_packets++;
- stats->rx_bytes += skb->len;
- u64_stats_update_end(&stats->syncp);
+ return true;
+}
- gro_cells_receive(&vxlan->gro_cells, skb);
+static bool vxlan_ecn_decapsulate(struct vxlan_sock *vs, void *oiph,
+ struct sk_buff *skb)
+{
+ int err = 0;
- return;
-drop:
- if (tun_dst)
- dst_release((struct dst_entry *)tun_dst);
+ if (vxlan_get_sk_family(vs) == AF_INET)
+ err = IP_ECN_decapsulate(oiph, skb);
+#if IS_ENABLED(CONFIG_IPV6)
+ else
+ err = IP6_ECN_decapsulate(oiph, skb);
+#endif
- /* Consume bad packet */
- kfree_skb(skb);
+ if (unlikely(err) && log_ecn_error) {
+ if (vxlan_get_sk_family(vs) == AF_INET)
+ net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
+ &((struct iphdr *)oiph)->saddr,
+ ((struct iphdr *)oiph)->tos);
+ else
+ net_info_ratelimited("non-ECT from %pI6\n",
+ &((struct ipv6hdr *)oiph)->saddr);
+ }
+ return err <= 1;
}
/* Callback from net/ipv4/udp.c to receive packets */
-static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+static int vxlan_rcv(struct sock *sk, struct sk_buff *skb)
{
- struct metadata_dst *tun_dst = NULL;
+ struct pcpu_sw_netstats *stats;
+ struct vxlan_dev *vxlan;
struct vxlan_sock *vs;
- struct vxlanhdr *vxh;
- u32 flags, vni;
+ struct vxlanhdr unparsed;
struct vxlan_metadata _md;
struct vxlan_metadata *md = &_md;
+ void *oiph;
/* Need Vxlan and inner Ethernet header to be present */
if (!pskb_may_pull(skb, VXLAN_HLEN))
- goto error;
-
- vxh = (struct vxlanhdr *)(udp_hdr(skb) + 1);
- flags = ntohl(vxh->vx_flags);
- vni = ntohl(vxh->vx_vni);
+ return 1;
- if (flags & VXLAN_HF_VNI) {
- flags &= ~VXLAN_HF_VNI;
- } else {
- /* VNI flag always required to be set */
- goto bad_flags;
+ unparsed = *vxlan_hdr(skb);
+ /* VNI flag always required to be set */
+ if (!(unparsed.vx_flags & VXLAN_HF_VNI)) {
+ netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n",
+ ntohl(vxlan_hdr(skb)->vx_flags),
+ ntohl(vxlan_hdr(skb)->vx_vni));
+ /* Return non vxlan pkt */
+ return 1;
}
-
- if (iptunnel_pull_header(skb, VXLAN_HLEN, htons(ETH_P_TEB)))
- goto drop;
- vxh = (struct vxlanhdr *)(udp_hdr(skb) + 1);
+ unparsed.vx_flags &= ~VXLAN_HF_VNI;
+ unparsed.vx_vni &= ~VXLAN_VNI_MASK;
vs = rcu_dereference_sk_user_data(sk);
if (!vs)
goto drop;
- if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) {
- vxh = vxlan_remcsum(skb, vxh, sizeof(struct vxlanhdr), vni,
- !!(vs->flags & VXLAN_F_REMCSUM_NOPARTIAL));
- if (!vxh)
- goto drop;
+ vxlan = vxlan_vs_find_vni(vs, vxlan_vni(vxlan_hdr(skb)->vx_vni));
+ if (!vxlan)
+ goto drop;
- flags &= ~VXLAN_HF_RCO;
- vni &= VXLAN_VNI_MASK;
- }
+ if (iptunnel_pull_header(skb, VXLAN_HLEN, htons(ETH_P_TEB),
+ !net_eq(vxlan->net, dev_net(vxlan->dev))))
+ goto drop;
if (vxlan_collect_metadata(vs)) {
+ __be32 vni = vxlan_vni(vxlan_hdr(skb)->vx_vni);
+ struct metadata_dst *tun_dst;
+
tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), TUNNEL_KEY,
- cpu_to_be64(vni >> 8), sizeof(*md));
+ vxlan_vni_to_tun_id(vni), sizeof(*md));
if (!tun_dst)
goto drop;
md = ip_tunnel_info_opts(&tun_dst->u.tun_info);
+
+ skb_dst_set(skb, (struct dst_entry *)tun_dst);
} else {
memset(md, 0, sizeof(*md));
}
/* For backwards compatibility, only allow reserved fields to be
* used by VXLAN extensions if explicitly requested.
*/
- if ((flags & VXLAN_HF_GBP) && (vs->flags & VXLAN_F_GBP)) {
- struct vxlanhdr_gbp *gbp;
-
- gbp = (struct vxlanhdr_gbp *)vxh;
- md->gbp = ntohs(gbp->policy_id);
-
- if (tun_dst) {
- tun_dst->u.tun_info.key.tun_flags |= TUNNEL_VXLAN_OPT;
- tun_dst->u.tun_info.options_len = sizeof(*md);
- }
-
- if (gbp->dont_learn)
- md->gbp |= VXLAN_GBP_DONT_LEARN;
-
- if (gbp->policy_applied)
- md->gbp |= VXLAN_GBP_POLICY_APPLIED;
-
- flags &= ~VXLAN_GBP_USED_BITS;
- }
+ if (vs->flags & VXLAN_F_REMCSUM_RX)
+ if (!vxlan_remcsum(&unparsed, skb, vs->flags))
+ goto drop;
+ if (vs->flags & VXLAN_F_GBP)
+ vxlan_parse_gbp_hdr(&unparsed, skb, vs->flags, md);
- if (flags || vni & ~VXLAN_VNI_MASK) {
+ if (unparsed.vx_flags || unparsed.vx_vni) {
/* If there are any unprocessed flags remaining treat
* this as a malformed packet. This behavior diverges from
* VXLAN RFC (RFC7348) which stipulates that bits in reserved
* is more robust and provides a little more security in
* adding extensions to VXLAN.
*/
+ goto drop;
+ }
- goto bad_flags;
+ if (!vxlan_set_mac(vxlan, vs, skb))
+ goto drop;
+
+ oiph = skb_network_header(skb);
+ skb_reset_network_header(skb);
+
+ if (!vxlan_ecn_decapsulate(vs, oiph, skb)) {
+ ++vxlan->dev->stats.rx_frame_errors;
+ ++vxlan->dev->stats.rx_errors;
+ goto drop;
}
- vxlan_rcv(vs, skb, md, vni >> 8, tun_dst);
+ stats = this_cpu_ptr(vxlan->dev->tstats);
+ u64_stats_update_begin(&stats->syncp);
+ stats->rx_packets++;
+ stats->rx_bytes += skb->len;
+ u64_stats_update_end(&stats->syncp);
+
+ gro_cells_receive(&vxlan->gro_cells, skb);
return 0;
drop:
/* Consume bad packet */
kfree_skb(skb);
return 0;
-
-bad_flags:
- netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n",
- ntohl(vxh->vx_flags), ntohl(vxh->vx_vni));
-
-error:
- if (tun_dst)
- dst_release((struct dst_entry *)tun_dst);
-
- /* Return non vxlan pkt */
- return 1;
}
static int arp_reduce(struct net_device *dev, struct sk_buff *skb)
reply->dev = dev;
skb_reserve(reply, LL_RESERVED_SPACE(request->dev));
skb_push(reply, sizeof(struct ethhdr));
- skb_set_mac_header(reply, 0);
+ skb_reset_mac_header(reply);
ns = (struct nd_msg *)skb_transport_header(request);
reply->protocol = htons(ETH_P_IPV6);
skb_pull(reply, sizeof(struct ethhdr));
- skb_set_network_header(reply, 0);
+ skb_reset_network_header(reply);
skb_put(reply, sizeof(struct ipv6hdr));
/* IPv6 header */
pip6->saddr = *(struct in6_addr *)n->primary_key;
skb_pull(reply, sizeof(struct ipv6hdr));
- skb_set_transport_header(reply, 0);
+ skb_reset_transport_header(reply);
na = (struct nd_msg *)skb_put(reply, sizeof(*na) + na_olen);
return;
gbp = (struct vxlanhdr_gbp *)vxh;
- vxh->vx_flags |= htonl(VXLAN_HF_GBP);
+ vxh->vx_flags |= VXLAN_HF_GBP;
if (md->gbp & VXLAN_GBP_DONT_LEARN)
gbp->dont_learn = 1;
gbp->policy_id = htons(md->gbp & VXLAN_GBP_ID_MASK);
}
-#if IS_ENABLED(CONFIG_IPV6)
-static int vxlan6_xmit_skb(struct dst_entry *dst, struct sock *sk,
- 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,
- struct vxlan_metadata *md, bool xnet, u32 vxflags)
+static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst,
+ int iphdr_len, __be32 vni,
+ struct vxlan_metadata *md, u32 vxflags,
+ bool udp_sum)
{
struct vxlanhdr *vxh;
int min_headroom;
int err;
- bool udp_sum = !(vxflags & VXLAN_F_UDP_ZERO_CSUM6_TX);
int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
- u16 hdrlen = sizeof(struct vxlanhdr);
if ((vxflags & VXLAN_F_REMCSUM_TX) &&
skb->ip_summed == CHECKSUM_PARTIAL) {
if (csum_start <= VXLAN_MAX_REMCSUM_START &&
!(csum_start & VXLAN_RCO_SHIFT_MASK) &&
(skb->csum_offset == offsetof(struct udphdr, check) ||
- skb->csum_offset == offsetof(struct tcphdr, check))) {
- udp_sum = false;
+ skb->csum_offset == offsetof(struct tcphdr, check)))
type |= SKB_GSO_TUNNEL_REMCSUM;
- }
}
- skb_scrub_packet(skb, xnet);
-
min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len
- + VXLAN_HLEN + sizeof(struct ipv6hdr)
+ + VXLAN_HLEN + iphdr_len
+ (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
/* Need space for new headers (invalidates iph ptr) */
err = skb_cow_head(skb, min_headroom);
if (unlikely(err)) {
kfree_skb(skb);
- goto err;
+ return err;
}
skb = vlan_hwaccel_push_inside(skb);
- if (WARN_ON(!skb)) {
- err = -ENOMEM;
- goto err;
- }
+ if (WARN_ON(!skb))
+ return -ENOMEM;
- skb = iptunnel_handle_offloads(skb, udp_sum, type);
- if (IS_ERR(skb)) {
- err = -EINVAL;
- goto err;
- }
+ skb = iptunnel_handle_offloads(skb, type);
+ if (IS_ERR(skb))
+ return PTR_ERR(skb);
vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
- vxh->vx_flags = htonl(VXLAN_HF_VNI);
- vxh->vx_vni = vni;
+ vxh->vx_flags = VXLAN_HF_VNI;
+ vxh->vx_vni = vxlan_vni_field(vni);
if (type & SKB_GSO_TUNNEL_REMCSUM) {
- u32 data = (skb_checksum_start_offset(skb) - hdrlen) >>
- VXLAN_RCO_SHIFT;
+ unsigned int start;
- if (skb->csum_offset == offsetof(struct udphdr, check))
- data |= VXLAN_RCO_UDP;
-
- vxh->vx_vni |= htonl(data);
- vxh->vx_flags |= htonl(VXLAN_HF_RCO);
+ start = skb_checksum_start_offset(skb) - sizeof(struct vxlanhdr);
+ vxh->vx_vni |= vxlan_compute_rco(start, skb->csum_offset);
+ vxh->vx_flags |= VXLAN_HF_RCO;
if (!skb_is_gso(skb)) {
skb->ip_summed = CHECKSUM_NONE;
vxlan_build_gbp_hdr(vxh, vxflags, md);
skb_set_inner_protocol(skb, htons(ETH_P_TEB));
-
- udp_tunnel6_xmit_skb(dst, sk, skb, dev, saddr, daddr, prio,
- ttl, src_port, dst_port,
- !!(vxflags & VXLAN_F_UDP_ZERO_CSUM6_TX));
return 0;
-err:
- dst_release(dst);
- return err;
}
-#endif
-static int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
- __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
- __be16 src_port, __be16 dst_port, __be32 vni,
- struct vxlan_metadata *md, bool xnet, u32 vxflags)
+static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan,
+ struct sk_buff *skb, int oif, u8 tos,
+ __be32 daddr, __be32 *saddr,
+ struct dst_cache *dst_cache,
+ const struct ip_tunnel_info *info)
{
- struct vxlanhdr *vxh;
- int min_headroom;
- int err;
- bool udp_sum = !!(vxflags & VXLAN_F_UDP_CSUM);
- int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
- u16 hdrlen = sizeof(struct vxlanhdr);
-
- if ((vxflags & VXLAN_F_REMCSUM_TX) &&
- skb->ip_summed == CHECKSUM_PARTIAL) {
- int csum_start = skb_checksum_start_offset(skb);
+ bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
+ struct rtable *rt = NULL;
+ struct flowi4 fl4;
- if (csum_start <= VXLAN_MAX_REMCSUM_START &&
- !(csum_start & VXLAN_RCO_SHIFT_MASK) &&
- (skb->csum_offset == offsetof(struct udphdr, check) ||
- skb->csum_offset == offsetof(struct tcphdr, check))) {
- udp_sum = false;
- type |= SKB_GSO_TUNNEL_REMCSUM;
- }
+ if (tos && !info)
+ use_cache = false;
+ if (use_cache) {
+ rt = dst_cache_get_ip4(dst_cache, saddr);
+ if (rt)
+ return rt;
}
- min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
- + VXLAN_HLEN + sizeof(struct iphdr)
- + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
-
- /* Need space for new headers (invalidates iph ptr) */
- err = skb_cow_head(skb, min_headroom);
- if (unlikely(err)) {
- kfree_skb(skb);
- return err;
- }
-
- skb = vlan_hwaccel_push_inside(skb);
- if (WARN_ON(!skb))
- return -ENOMEM;
-
- skb = iptunnel_handle_offloads(skb, udp_sum, type);
- if (IS_ERR(skb))
- return PTR_ERR(skb);
-
- vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
- vxh->vx_flags = htonl(VXLAN_HF_VNI);
- vxh->vx_vni = vni;
-
- if (type & SKB_GSO_TUNNEL_REMCSUM) {
- u32 data = (skb_checksum_start_offset(skb) - hdrlen) >>
- VXLAN_RCO_SHIFT;
-
- if (skb->csum_offset == offsetof(struct udphdr, check))
- data |= VXLAN_RCO_UDP;
-
- vxh->vx_vni |= htonl(data);
- vxh->vx_flags |= htonl(VXLAN_HF_RCO);
+ memset(&fl4, 0, sizeof(fl4));
+ fl4.flowi4_oif = oif;
+ fl4.flowi4_tos = RT_TOS(tos);
+ fl4.flowi4_mark = skb->mark;
+ fl4.flowi4_proto = IPPROTO_UDP;
+ fl4.daddr = daddr;
+ fl4.saddr = vxlan->cfg.saddr.sin.sin_addr.s_addr;
- if (!skb_is_gso(skb)) {
- skb->ip_summed = CHECKSUM_NONE;
- skb->encapsulation = 0;
- }
+ rt = ip_route_output_key(vxlan->net, &fl4);
+ if (!IS_ERR(rt)) {
+ *saddr = fl4.saddr;
+ if (use_cache)
+ dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr);
}
-
- if (vxflags & VXLAN_F_GBP)
- vxlan_build_gbp_hdr(vxh, vxflags, md);
-
- skb_set_inner_protocol(skb, htons(ETH_P_TEB));
-
- udp_tunnel_xmit_skb(rt, sk, skb, src, dst, tos, ttl, df,
- src_port, dst_port, xnet,
- !(vxflags & VXLAN_F_UDP_CSUM));
- return 0;
+ return rt;
}
#if IS_ENABLED(CONFIG_IPV6)
static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
- struct sk_buff *skb, int oif,
+ struct sk_buff *skb, int oif, u8 tos,
+ __be32 label,
const struct in6_addr *daddr,
- struct in6_addr *saddr)
+ struct in6_addr *saddr,
+ struct dst_cache *dst_cache,
+ const struct ip_tunnel_info *info)
{
+ bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct dst_entry *ndst;
struct flowi6 fl6;
int err;
+ if (tos && !info)
+ use_cache = false;
+ if (use_cache) {
+ ndst = dst_cache_get_ip6(dst_cache, saddr);
+ if (ndst)
+ return ndst;
+ }
+
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = oif;
fl6.daddr = *daddr;
fl6.saddr = vxlan->cfg.saddr.sin6.sin6_addr;
+ fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tos), label);
fl6.flowi6_mark = skb->mark;
fl6.flowi6_proto = IPPROTO_UDP;
return ERR_PTR(err);
*saddr = fl6.saddr;
+ if (use_cache)
+ dst_cache_set_ip6(dst_cache, ndst, saddr);
return ndst;
}
#endif
static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
struct vxlan_rdst *rdst, bool did_rsc)
{
+ struct dst_cache *dst_cache;
struct ip_tunnel_info *info;
struct vxlan_dev *vxlan = netdev_priv(dev);
struct sock *sk;
struct rtable *rt = NULL;
const struct iphdr *old_iph;
- struct flowi4 fl4;
union vxlan_addr *dst;
union vxlan_addr remote_ip;
struct vxlan_metadata _md;
struct vxlan_metadata *md = &_md;
__be16 src_port = 0, dst_port;
- u32 vni;
+ __be32 vni, label;
__be16 df = 0;
__u8 tos, ttl;
int err;
u32 flags = vxlan->flags;
+ bool udp_sum = false;
+ bool xnet = !net_eq(vxlan->net, dev_net(vxlan->dev));
info = skb_tunnel_info(skb);
dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port;
vni = rdst->remote_vni;
dst = &rdst->remote_ip;
+ dst_cache = &rdst->dst_cache;
} else {
if (!info) {
WARN_ONCE(1, "%s: Missing encapsulation instructions\n",
goto drop;
}
dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port;
- vni = be64_to_cpu(info->key.tun_id);
+ vni = vxlan_tun_id_to_vni(info->key.tun_id);
remote_ip.sa.sa_family = ip_tunnel_info_af(info);
if (remote_ip.sa.sa_family == AF_INET)
remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst;
else
remote_ip.sin6.sin6_addr = info->key.u.ipv6.dst;
dst = &remote_ip;
+ dst_cache = &info->dst_cache;
}
if (vxlan_addr_any(dst)) {
if (tos == 1)
tos = ip_tunnel_get_dsfield(old_iph, skb);
+ label = vxlan->cfg.label;
src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min,
vxlan->cfg.port_max, true);
if (info) {
ttl = info->key.ttl;
tos = info->key.tos;
+ label = info->key.label;
+ udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM);
if (info->options_len)
md = ip_tunnel_info_opts(info);
}
if (dst->sa.sa_family == AF_INET) {
+ __be32 saddr;
+
if (!vxlan->vn4_sock)
goto drop;
sk = vxlan->vn4_sock->sock->sk;
- if (info) {
- if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)
- df = htons(IP_DF);
-
- if (info->key.tun_flags & TUNNEL_CSUM)
- flags |= VXLAN_F_UDP_CSUM;
- else
- flags &= ~VXLAN_F_UDP_CSUM;
- }
-
- memset(&fl4, 0, sizeof(fl4));
- fl4.flowi4_oif = rdst ? rdst->remote_ifindex : 0;
- fl4.flowi4_tos = RT_TOS(tos);
- fl4.flowi4_mark = skb->mark;
- fl4.flowi4_proto = IPPROTO_UDP;
- fl4.daddr = dst->sin.sin_addr.s_addr;
- fl4.saddr = vxlan->cfg.saddr.sin.sin_addr.s_addr;
-
- rt = ip_route_output_key(vxlan->net, &fl4);
+ rt = vxlan_get_route(vxlan, skb,
+ rdst ? rdst->remote_ifindex : 0, tos,
+ dst->sin.sin_addr.s_addr, &saddr,
+ dst_cache, info);
if (IS_ERR(rt)) {
netdev_dbg(dev, "no route to %pI4\n",
&dst->sin.sin_addr.s_addr);
return;
}
+ if (!info)
+ udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX);
+ else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)
+ df = htons(IP_DF);
+
tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
- err = vxlan_xmit_skb(rt, sk, skb, fl4.saddr,
- dst->sin.sin_addr.s_addr, tos, ttl, df,
- src_port, dst_port, htonl(vni << 8), md,
- !net_eq(vxlan->net, dev_net(vxlan->dev)),
- flags);
- if (err < 0) {
- /* skb is already freed. */
- skb = NULL;
- goto rt_tx_error;
- }
+ err = vxlan_build_skb(skb, &rt->dst, sizeof(struct iphdr),
+ vni, md, flags, udp_sum);
+ if (err < 0)
+ goto xmit_tx_error;
+
+ udp_tunnel_xmit_skb(rt, sk, skb, saddr,
+ dst->sin.sin_addr.s_addr, tos, ttl, df,
+ src_port, dst_port, xnet, !udp_sum);
#if IS_ENABLED(CONFIG_IPV6)
} else {
struct dst_entry *ndst;
sk = vxlan->vn6_sock->sock->sk;
ndst = vxlan6_get_route(vxlan, skb,
- rdst ? rdst->remote_ifindex : 0,
- &dst->sin6.sin6_addr, &saddr);
+ rdst ? rdst->remote_ifindex : 0, tos,
+ label, &dst->sin6.sin6_addr, &saddr,
+ dst_cache, info);
if (IS_ERR(ndst)) {
netdev_dbg(dev, "no route to %pI6\n",
&dst->sin6.sin6_addr);
return;
}
- if (info) {
- if (info->key.tun_flags & TUNNEL_CSUM)
- flags &= ~VXLAN_F_UDP_ZERO_CSUM6_TX;
- else
- flags |= VXLAN_F_UDP_ZERO_CSUM6_TX;
- }
+ if (!info)
+ udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
+ tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
ttl = ttl ? : ip6_dst_hoplimit(ndst);
- err = vxlan6_xmit_skb(ndst, sk, skb, dev, &saddr, &dst->sin6.sin6_addr,
- 0, ttl, src_port, dst_port, htonl(vni << 8), md,
- !net_eq(vxlan->net, dev_net(vxlan->dev)),
- flags);
+ skb_scrub_packet(skb, xnet);
+ err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr),
+ vni, md, flags, udp_sum);
+ if (err < 0) {
+ dst_release(ndst);
+ return;
+ }
+ udp_tunnel6_xmit_skb(ndst, sk, skb, dev,
+ &saddr, &dst->sin6.sin6_addr, tos, ttl,
+ label, src_port, dst_port, !udp_sum);
#endif
}
dev->stats.tx_dropped++;
goto tx_free;
+xmit_tx_error:
+ /* skb is already freed. */
+ skb = NULL;
rt_tx_error:
ip_rt_put(rt);
tx_error:
static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan)
{
struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
- __u32 vni = vxlan->default_dst.remote_vni;
+ __be32 vni = vxlan->default_dst.remote_vni;
spin_lock(&vn->sock_lock);
hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni));
return __vxlan_change_mtu(dev, lowerdev, dst, new_mtu, true);
}
-static int egress_ipv4_tun_info(struct net_device *dev, struct sk_buff *skb,
- struct ip_tunnel_info *info,
- __be16 sport, __be16 dport)
-{
- struct vxlan_dev *vxlan = netdev_priv(dev);
- struct rtable *rt;
- struct flowi4 fl4;
-
- memset(&fl4, 0, sizeof(fl4));
- fl4.flowi4_tos = RT_TOS(info->key.tos);
- fl4.flowi4_mark = skb->mark;
- fl4.flowi4_proto = IPPROTO_UDP;
- fl4.daddr = info->key.u.ipv4.dst;
-
- rt = ip_route_output_key(vxlan->net, &fl4);
- if (IS_ERR(rt))
- return PTR_ERR(rt);
- ip_rt_put(rt);
-
- info->key.u.ipv4.src = fl4.saddr;
- info->key.tp_src = sport;
- info->key.tp_dst = dport;
- return 0;
-}
-
static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
dport = info->key.tp_dst ? : vxlan->cfg.dst_port;
if (ip_tunnel_info_af(info) == AF_INET) {
+ struct rtable *rt;
+
if (!vxlan->vn4_sock)
return -EINVAL;
- return egress_ipv4_tun_info(dev, skb, info, sport, dport);
+ rt = vxlan_get_route(vxlan, skb, 0, info->key.tos,
+ info->key.u.ipv4.dst,
+ &info->key.u.ipv4.src, NULL, info);
+ if (IS_ERR(rt))
+ return PTR_ERR(rt);
+ ip_rt_put(rt);
} else {
#if IS_ENABLED(CONFIG_IPV6)
struct dst_entry *ndst;
if (!vxlan->vn6_sock)
return -EINVAL;
- ndst = vxlan6_get_route(vxlan, skb, 0,
- &info->key.u.ipv6.dst,
- &info->key.u.ipv6.src);
+ ndst = vxlan6_get_route(vxlan, skb, 0, info->key.tos,
+ info->key.label, &info->key.u.ipv6.dst,
+ &info->key.u.ipv6.src, NULL, info);
if (IS_ERR(ndst))
return PTR_ERR(ndst);
dst_release(ndst);
-
- info->key.tp_src = sport;
- info->key.tp_dst = dport;
#else /* !CONFIG_IPV6 */
return -EPFNOSUPPORT;
#endif
}
+ info->key.tp_src = sport;
+ info->key.tp_dst = dport;
return 0;
}
[IFLA_VXLAN_LOCAL6] = { .len = sizeof(struct in6_addr) },
[IFLA_VXLAN_TOS] = { .type = NLA_U8 },
[IFLA_VXLAN_TTL] = { .type = NLA_U8 },
+ [IFLA_VXLAN_LABEL] = { .type = NLA_U32 },
[IFLA_VXLAN_LEARNING] = { .type = NLA_U8 },
[IFLA_VXLAN_AGEING] = { .type = NLA_U32 },
[IFLA_VXLAN_LIMIT] = { .type = NLA_U32 },
/* Mark socket as an encapsulation socket. */
tunnel_cfg.sk_user_data = vs;
tunnel_cfg.encap_type = 1;
- tunnel_cfg.encap_rcv = vxlan_udp_encap_recv;
+ tunnel_cfg.encap_rcv = vxlan_rcv;
tunnel_cfg.encap_destroy = NULL;
setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
vxlan->flags |= VXLAN_F_IPV6;
}
+ if (conf->label && !use_ipv6) {
+ pr_info("label only supported in use with IPv6\n");
+ return -EINVAL;
+ }
+
if (conf->remote_ifindex) {
lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex);
dst->remote_ifindex = conf->remote_ifindex;
memset(&conf, 0, sizeof(conf));
if (data[IFLA_VXLAN_ID])
- conf.vni = nla_get_u32(data[IFLA_VXLAN_ID]);
+ conf.vni = cpu_to_be32(nla_get_u32(data[IFLA_VXLAN_ID]));
if (data[IFLA_VXLAN_GROUP]) {
conf.remote_ip.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]);
if (data[IFLA_VXLAN_TTL])
conf.ttl = nla_get_u8(data[IFLA_VXLAN_TTL]);
+ if (data[IFLA_VXLAN_LABEL])
+ conf.label = nla_get_be32(data[IFLA_VXLAN_LABEL]) &
+ IPV6_FLOWLABEL_MASK;
+
if (!data[IFLA_VXLAN_LEARNING] || nla_get_u8(data[IFLA_VXLAN_LEARNING]))
conf.flags |= VXLAN_F_LEARN;
if (data[IFLA_VXLAN_PORT])
conf.dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]);
- if (data[IFLA_VXLAN_UDP_CSUM] && nla_get_u8(data[IFLA_VXLAN_UDP_CSUM]))
- conf.flags |= VXLAN_F_UDP_CSUM;
+ if (data[IFLA_VXLAN_UDP_CSUM] &&
+ !nla_get_u8(data[IFLA_VXLAN_UDP_CSUM]))
+ conf.flags |= VXLAN_F_UDP_ZERO_CSUM_TX;
if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX] &&
nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]))
break;
case -EEXIST:
- pr_info("duplicate VNI %u\n", conf.vni);
+ pr_info("duplicate VNI %u\n", be32_to_cpu(conf.vni));
break;
}
nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_LOCAL{6} */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */
+ nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_PROXY */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_RSC */
.high = htons(vxlan->cfg.port_max),
};
- if (nla_put_u32(skb, IFLA_VXLAN_ID, dst->remote_vni))
+ if (nla_put_u32(skb, IFLA_VXLAN_ID, be32_to_cpu(dst->remote_vni)))
goto nla_put_failure;
if (!vxlan_addr_any(&dst->remote_ip)) {
if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) ||
nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) ||
+ nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) ||
nla_put_u8(skb, IFLA_VXLAN_LEARNING,
!!(vxlan->flags & VXLAN_F_LEARN)) ||
nla_put_u8(skb, IFLA_VXLAN_PROXY,
nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->cfg.addrmax) ||
nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->cfg.dst_port) ||
nla_put_u8(skb, IFLA_VXLAN_UDP_CSUM,
- !!(vxlan->flags & VXLAN_F_UDP_CSUM)) ||
+ !(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM_TX)) ||
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,