| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Fri, 1 Aug 2014 14:54:43 -0700
From: Andy Zhou <azhou@...ira.com>
To: davem@...emloft.net
Cc: netdev@...r.kernel.org, Andy Zhou <azhou@...ira.com>
Subject: [net-next 3/5] net: Refactor vxlan driver to make use of common UDP tunnel functions
Refactor vxlan driver to make use of the common UDP tunnel
functions.
Signed-off-by: Andy Zhou <azhou@...ira.com>
---
drivers/net/ethernet/emulex/benet/be_main.c | 16 +-
drivers/net/ethernet/intel/i40e/i40e_main.c | 18 +-
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 18 +-
drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 18 +-
drivers/net/vxlan.c | 275 ++++++----------------
include/linux/netdevice.h | 43 ++--
include/net/vxlan.h | 23 +-
net/ipv4/udp_tunnel.c | 8 +-
net/openvswitch/vport-vxlan.c | 6 +-
9 files changed, 161 insertions(+), 264 deletions(-)
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index f8cbd9a..6932787 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -2921,7 +2921,7 @@ static int be_open(struct net_device *netdev)
#ifdef CONFIG_BE2NET_VXLAN
if (skyhawk_chip(adapter))
- vxlan_get_rx_port(netdev);
+ udp_tunnel_get_rx_port(netdev);
#endif
return 0;
@@ -4324,7 +4324,7 @@ static int be_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
#ifdef CONFIG_BE2NET_VXLAN
static void be_add_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
- __be16 port)
+ __be16 port, u64 protocol_bit)
{
struct be_adapter *adapter = netdev_priv(netdev);
struct device *dev = &adapter->pdev->dev;
@@ -4333,6 +4333,9 @@ static void be_add_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
if (lancer_chip(adapter) || BEx_chip(adapter))
return;
+ if (protocol_bit != NETIF_F_RX_UT_VXLAN)
+ return;
+
if (adapter->flags & BE_FLAGS_VXLAN_OFFLOADS) {
dev_warn(dev, "Cannot add UDP port %d for VxLAN offloads\n",
be16_to_cpu(port));
@@ -4365,13 +4368,16 @@ err:
}
static void be_del_vxlan_port(struct net_device *netdev, sa_family_t sa_family,
- __be16 port)
+ __be16 port, u64 protocol_bit)
{
struct be_adapter *adapter = netdev_priv(netdev);
if (lancer_chip(adapter) || BEx_chip(adapter))
return;
+ if (protocol_bit != NETIF_F_RX_UT_VXLAN)
+ return;
+
if (adapter->vxlan_port != port)
return;
@@ -4408,8 +4414,8 @@ static const struct net_device_ops be_netdev_ops = {
.ndo_busy_poll = be_busy_poll,
#endif
#ifdef CONFIG_BE2NET_VXLAN
- .ndo_add_vxlan_port = be_add_vxlan_port,
- .ndo_del_vxlan_port = be_del_vxlan_port,
+ .ndo_add_udp_tunnel_port = be_add_vxlan_port,
+ .ndo_del_udp_tunnel_port = be_del_vxlan_port,
#endif
};
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index a77ad6d..343a110 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -4526,7 +4526,7 @@ static int i40e_open(struct net_device *netdev)
wr32(&pf->hw, I40E_GLLAN_TSOMSK_L, be32_to_cpu(TCP_FLAG_CWR) >> 16);
#ifdef CONFIG_I40E_VXLAN
- vxlan_get_rx_port(netdev);
+ udp_tunnel_get_rx_port(netdev);
#endif
return 0;
@@ -6946,7 +6946,8 @@ static u8 i40e_get_vxlan_port_idx(struct i40e_pf *pf, __be16 port)
* @port: New UDP port number that VXLAN started listening to
**/
static void i40e_add_vxlan_port(struct net_device *netdev,
- sa_family_t sa_family, __be16 port)
+ sa_family_t sa_family, __be16 port,
+ u64 protocol_bit)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
@@ -6957,6 +6958,9 @@ static void i40e_add_vxlan_port(struct net_device *netdev,
if (sa_family == AF_INET6)
return;
+ if (protocol_bit != NETIF_F_RX_UT_VXLAN)
+ return;
+
idx = i40e_get_vxlan_port_idx(pf, port);
/* Check if port already exists */
@@ -6988,7 +6992,8 @@ static void i40e_add_vxlan_port(struct net_device *netdev,
* @port: UDP port number that VXLAN stopped listening to
**/
static void i40e_del_vxlan_port(struct net_device *netdev,
- sa_family_t sa_family, __be16 port)
+ sa_family_t sa_family, __be16 port,
+ u64 protocol_bit)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
@@ -6998,6 +7003,9 @@ static void i40e_del_vxlan_port(struct net_device *netdev,
if (sa_family == AF_INET6)
return;
+ if (protocol_bit != NETIF_F_RX_UT_VXLAN)
+ return;
+
idx = i40e_get_vxlan_port_idx(pf, port);
/* Check if port already exists */
@@ -7149,8 +7157,8 @@ static const struct net_device_ops i40e_netdev_ops = {
.ndo_set_vf_link_state = i40e_ndo_set_vf_link_state,
.ndo_set_vf_spoofchk = i40e_ndo_set_vf_spoofck,
#ifdef CONFIG_I40E_VXLAN
- .ndo_add_vxlan_port = i40e_add_vxlan_port,
- .ndo_del_vxlan_port = i40e_del_vxlan_port,
+ .ndo_add_udp_tunnel_port = i40e_add_vxlan_port,
+ .ndo_del_udp_tunnel_port = i40e_del_vxlan_port,
#endif
.ndo_get_phys_port_id = i40e_get_phys_port_id,
#ifdef HAVE_FDB_OPS
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index e563b55..cf41622 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1721,7 +1721,7 @@ int mlx4_en_start_port(struct net_device *dev)
#ifdef CONFIG_MLX4_EN_VXLAN
if (priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS)
- vxlan_get_rx_port(dev);
+ udp_tunnel_get_rx_port(dev);
#endif
priv->port_up = true;
netif_tx_start_all_queues(dev);
@@ -2327,7 +2327,8 @@ static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
}
static void mlx4_en_add_vxlan_port(struct net_device *dev,
- sa_family_t sa_family, __be16 port)
+ sa_family_t sa_family, __be16 port,
+ u64 protocol_bit)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
__be16 current_port;
@@ -2338,6 +2339,9 @@ static void mlx4_en_add_vxlan_port(struct net_device *dev,
if (sa_family == AF_INET6)
return;
+ if (protocol_bit != NETIF_F_RX_UT_VXLAN)
+ return;
+
current_port = priv->vxlan_port;
if (current_port && current_port != port) {
en_warn(priv, "vxlan port %d configured, can't add port %d\n",
@@ -2350,7 +2354,8 @@ static void mlx4_en_add_vxlan_port(struct net_device *dev,
}
static void mlx4_en_del_vxlan_port(struct net_device *dev,
- sa_family_t sa_family, __be16 port)
+ sa_family_t sa_family, __be16 port,
+ u64 protocol_bit)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
__be16 current_port;
@@ -2361,6 +2366,9 @@ static void mlx4_en_del_vxlan_port(struct net_device *dev,
if (sa_family == AF_INET6)
return;
+ if (protocol_bit != NETIF_F_RX_UT_VXLAN)
+ return;
+
current_port = priv->vxlan_port;
if (current_port != port) {
en_dbg(DRV, priv, "vxlan port %d isn't configured, ignoring\n", ntohs(port));
@@ -2398,8 +2406,8 @@ static const struct net_device_ops mlx4_netdev_ops = {
#endif
.ndo_get_phys_port_id = mlx4_en_get_phys_port_id,
#ifdef CONFIG_MLX4_EN_VXLAN
- .ndo_add_vxlan_port = mlx4_en_add_vxlan_port,
- .ndo_del_vxlan_port = mlx4_en_del_vxlan_port,
+ .ndo_add_udp_tunnel_port = mlx4_en_add_vxlan_port,
+ .ndo_del_udp_tunnel_port = mlx4_en_del_vxlan_port,
#endif
};
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 227cfb1..37ab266 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -470,7 +470,8 @@ static int qlcnic_get_phys_port_id(struct net_device *netdev,
#ifdef CONFIG_QLCNIC_VXLAN
static void qlcnic_add_vxlan_port(struct net_device *netdev,
- sa_family_t sa_family, __be16 port)
+ sa_family_t sa_family, __be16 port,
+ u64 protocol_bit)
{
struct qlcnic_adapter *adapter = netdev_priv(netdev);
struct qlcnic_hardware_context *ahw = adapter->ahw;
@@ -481,12 +482,16 @@ static void qlcnic_add_vxlan_port(struct net_device *netdev,
if (!qlcnic_encap_rx_offload(adapter) || ahw->vxlan_port)
return;
+ if (protocol_bit != NETIF_F_RX_UT_VXLAN)
+ return;
+
ahw->vxlan_port = ntohs(port);
adapter->flags |= QLCNIC_ADD_VXLAN_PORT;
}
static void qlcnic_del_vxlan_port(struct net_device *netdev,
- sa_family_t sa_family, __be16 port)
+ sa_family_t sa_family, __be16 port,
+ u64 protocol_bit)
{
struct qlcnic_adapter *adapter = netdev_priv(netdev);
struct qlcnic_hardware_context *ahw = adapter->ahw;
@@ -495,6 +500,9 @@ static void qlcnic_del_vxlan_port(struct net_device *netdev,
(ahw->vxlan_port != ntohs(port)))
return;
+ if (protocol_bit != NETIF_F_RX_UT_VXLAN)
+ return;
+
adapter->flags |= QLCNIC_DEL_VXLAN_PORT;
}
#endif
@@ -518,8 +526,8 @@ static const struct net_device_ops qlcnic_netdev_ops = {
.ndo_fdb_dump = qlcnic_fdb_dump,
.ndo_get_phys_port_id = qlcnic_get_phys_port_id,
#ifdef CONFIG_QLCNIC_VXLAN
- .ndo_add_vxlan_port = qlcnic_add_vxlan_port,
- .ndo_del_vxlan_port = qlcnic_del_vxlan_port,
+ .ndo_add_udp_tunnel_port = qlcnic_add_vxlan_port,
+ .ndo_del_udp_tunnel_port = qlcnic_del_vxlan_port,
#endif
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = qlcnic_poll_controller,
@@ -1993,7 +2001,7 @@ qlcnic_attach(struct qlcnic_adapter *adapter)
#ifdef CONFIG_QLCNIC_VXLAN
if (qlcnic_encap_rx_offload(adapter))
- vxlan_get_rx_port(netdev);
+ udp_tunnel_get_rx_port(netdev);
#endif
adapter->is_up = QLCNIC_ADAPTER_UP_MAGIC;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 1fb7b37..65e3731 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -42,6 +42,7 @@
#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>
@@ -51,8 +52,6 @@
#define VXLAN_VERSION "0.1"
-#define PORT_HASH_BITS 8
-#define PORT_HASH_SIZE (1<<PORT_HASH_BITS)
#define VNI_HASH_BITS 10
#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
#define FDB_HASH_BITS 8
@@ -91,8 +90,7 @@ static const u8 all_zeros_mac[ETH_ALEN];
/* per-network namespace private data for this module */
struct vxlan_net {
struct list_head vxlan_list;
- struct hlist_head sock_list[PORT_HASH_SIZE];
- spinlock_t sock_lock;
+ spinlock_t vxlan_list_lock; /* protecting vxlan_list */
};
union vxlan_addr {
@@ -253,14 +251,6 @@ static inline struct hlist_head *vni_head(struct vxlan_sock *vs, u32 id)
return &vs->vni_list[hash_32(id, VNI_HASH_BITS)];
}
-/* Socket hash table head */
-static inline struct hlist_head *vs_head(struct net *net, __be16 port)
-{
- struct vxlan_net *vn = net_generic(net, vxlan_net_id);
-
- return &vn->sock_list[hash_32(ntohs(port), PORT_HASH_BITS)];
-}
-
/* First remote destination for a forwarding entry.
* Guaranteed to be non-NULL because remotes are never deleted.
*/
@@ -277,13 +267,7 @@ static inline struct vxlan_rdst *first_remote_rtnl(struct vxlan_fdb *fdb)
/* Find VXLAN socket based on network namespace and UDP port */
static struct vxlan_sock *vxlan_find_sock(struct net *net, __be16 port)
{
- struct vxlan_sock *vs;
-
- hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) {
- if (inet_sk(vs->sock->sk)->inet_sport == port)
- return vs;
- }
- return NULL;
+ return (struct vxlan_sock *)udp_tunnel_find_sock(net, port);
}
static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, u32 id)
@@ -636,7 +620,7 @@ static int vxlan_gro_complete(struct sk_buff *skb, int nhoff)
static void vxlan_notify_add_rx_port(struct vxlan_sock *vs)
{
struct net_device *dev;
- struct sock *sk = vs->sock->sk;
+ struct sock *sk = vs->uts.sock->sk;
struct net *net = sock_net(sk);
sa_family_t sa_family = sk->sk_family;
__be16 port = inet_sk(sk)->inet_sport;
@@ -650,9 +634,12 @@ static void vxlan_notify_add_rx_port(struct vxlan_sock *vs)
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
- if (dev->netdev_ops->ndo_add_vxlan_port)
- dev->netdev_ops->ndo_add_vxlan_port(dev, sa_family,
- port);
+ if (!(dev->features & NETIF_F_RX_UT_VXLAN))
+ continue;
+
+ if (dev->netdev_ops->ndo_add_udp_tunnel_port)
+ dev->netdev_ops->ndo_add_udp_tunnel_port(dev,
+ sa_family, port, NETIF_F_RX_UT_VXLAN);
}
rcu_read_unlock();
}
@@ -661,16 +648,19 @@ static void vxlan_notify_add_rx_port(struct vxlan_sock *vs)
static void vxlan_notify_del_rx_port(struct vxlan_sock *vs)
{
struct net_device *dev;
- struct sock *sk = vs->sock->sk;
+ struct sock *sk = vs->uts.sock->sk;
struct net *net = sock_net(sk);
sa_family_t sa_family = sk->sk_family;
__be16 port = inet_sk(sk)->inet_sport;
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
- if (dev->netdev_ops->ndo_del_vxlan_port)
- dev->netdev_ops->ndo_del_vxlan_port(dev, sa_family,
- port);
+ if (!(dev->features & vs->uts.protocol_bit))
+ continue;
+
+ if (dev->netdev_ops->ndo_del_udp_tunnel_port)
+ dev->netdev_ops->ndo_del_udp_tunnel_port(dev,
+ sa_family, port, vs->uts.protocol_bit);
}
rcu_read_unlock();
@@ -1053,19 +1043,11 @@ static void vxlan_sock_hold(struct vxlan_sock *vs)
void vxlan_sock_release(struct vxlan_sock *vs)
{
- struct sock *sk = vs->sock->sk;
- struct net *net = sock_net(sk);
- struct vxlan_net *vn = net_generic(net, vxlan_net_id);
-
if (!atomic_dec_and_test(&vs->refcnt))
return;
- spin_lock(&vn->sock_lock);
- hlist_del_rcu(&vs->hlist);
- rcu_assign_sk_user_data(vs->sock->sk, NULL);
+ udp_tunnel_sock_release(&vs->uts);
vxlan_notify_del_rx_port(vs);
- spin_unlock(&vn->sock_lock);
-
queue_work(vxlan_wq, &vs->del_work);
}
EXPORT_SYMBOL_GPL(vxlan_sock_release);
@@ -1078,7 +1060,7 @@ static void vxlan_igmp_join(struct work_struct *work)
{
struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_join);
struct vxlan_sock *vs = vxlan->vn_sock;
- struct sock *sk = vs->sock->sk;
+ struct sock *sk = vs->uts.sock->sk;
union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
int ifindex = vxlan->default_dst.remote_ifindex;
@@ -1107,7 +1089,7 @@ static void vxlan_igmp_leave(struct work_struct *work)
{
struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, igmp_leave);
struct vxlan_sock *vs = vxlan->vn_sock;
- struct sock *sk = vs->sock->sk;
+ struct sock *sk = vs->uts.sock->sk;
union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
int ifindex = vxlan->default_dst.remote_ifindex;
@@ -1338,7 +1320,6 @@ out:
}
#if IS_ENABLED(CONFIG_IPV6)
-
static struct sk_buff *vxlan_na_create(struct sk_buff *request,
struct neighbour *n, bool isrouter)
{
@@ -1572,13 +1553,6 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
return false;
}
-static inline struct sk_buff *vxlan_handle_offloads(struct sk_buff *skb,
- bool udp_csum)
-{
- 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)
static int vxlan6_xmit_skb(struct vxlan_sock *vs,
struct dst_entry *dst, struct sk_buff *skb,
@@ -1587,13 +1561,13 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
__be16 src_port, __be16 dst_port, __be32 vni,
bool xnet)
{
- struct ipv6hdr *ip6h;
struct vxlanhdr *vxh;
- struct udphdr *uh;
int min_headroom;
int err;
- skb = vxlan_handle_offloads(skb, !udp_get_no_check6_tx(vs->sock->sk));
+ skb = udp_tunnel_handle_offloads(skb,
+ !udp_get_no_check6_tx(
+ vs->uts.sock->sk));
if (IS_ERR(skb))
return -EINVAL;
@@ -1621,38 +1595,8 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
vxh->vx_flags = htonl(VXLAN_FLAGS);
vxh->vx_vni = vni;
- __skb_push(skb, sizeof(*uh));
- skb_reset_transport_header(skb);
- uh = udp_hdr(skb);
-
- uh->dest = dst_port;
- uh->source = src_port;
-
- uh->len = htons(skb->len);
-
- 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);
-
- 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);
- ip6h = ipv6_hdr(skb);
- ip6h->version = 6;
- ip6h->priority = prio;
- ip6h->flow_lbl[0] = 0;
- ip6h->flow_lbl[1] = 0;
- ip6h->flow_lbl[2] = 0;
- ip6h->payload_len = htons(skb->len);
- ip6h->nexthdr = IPPROTO_UDP;
- ip6h->hop_limit = ttl;
- ip6h->daddr = *daddr;
- ip6h->saddr = *saddr;
-
- ip6tunnel_xmit(skb, dev);
+ udp_tunnel6_xmit_skb(vs->uts.sock, dst, skb, dev, saddr, daddr, prio,
+ ttl, src_port, dst_port);
return 0;
}
#endif
@@ -1663,11 +1607,11 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
__be16 src_port, __be16 dst_port, __be32 vni, bool xnet)
{
struct vxlanhdr *vxh;
- struct udphdr *uh;
int min_headroom;
int err;
- skb = vxlan_handle_offloads(skb, !vs->sock->sk->sk_no_check_tx);
+ skb = udp_tunnel_handle_offloads(skb,
+ !vs->uts.sock->sk->sk_no_check_tx);
if (IS_ERR(skb))
return -EINVAL;
@@ -1693,20 +1637,8 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
vxh->vx_flags = htonl(VXLAN_FLAGS);
vxh->vx_vni = vni;
- __skb_push(skb, sizeof(*uh));
- skb_reset_transport_header(skb);
- uh = udp_hdr(skb);
-
- uh->dest = dst_port;
- uh->source = src_port;
-
- uh->len = htons(skb->len);
-
- udp_set_csum(vs->sock->sk->sk_no_check_tx, skb,
- src, dst, skb->len);
-
- return iptunnel_xmit(vs->sock->sk, rt, skb, src, dst, IPPROTO_UDP,
- tos, ttl, df, xnet);
+ return udp_tunnel_xmit_skb(vs->uts.sock, rt, skb, src, dst, tos,
+ ttl, df, src_port, dst_port, xnet);
}
EXPORT_SYMBOL_GPL(vxlan_xmit_skb);
@@ -1831,18 +1763,18 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
- 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),
- !net_eq(vxlan->net, dev_net(vxlan->dev)));
+ err = udp_tunnel_xmit_skb(vxlan->vn_sock->uts.sock, rt, skb,
+ fl4.saddr, dst->sin.sin_addr.s_addr,
+ tos, ttl, df, src_port, dst_port,
+ !net_eq(vxlan->net,
+ dev_net(vxlan->dev)));
if (err < 0)
goto rt_tx_error;
iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
#if IS_ENABLED(CONFIG_IPV6)
} else {
- struct sock *sk = vxlan->vn_sock->sock->sk;
+ struct sock *sk = vxlan->vn_sock->uts.sock->sk;
struct dst_entry *ndst;
struct flowi6 fl6;
u32 flags;
@@ -2038,7 +1970,7 @@ static int vxlan_init(struct net_device *dev)
if (!dev->tstats)
return -ENOMEM;
- spin_lock(&vn->sock_lock);
+ spin_lock(&vn->vxlan_list_lock);
vs = vxlan_find_sock(vxlan->net, vxlan->dst_port);
if (vs) {
/* If we have a socket with same port already, reuse it */
@@ -2049,7 +1981,7 @@ static int vxlan_init(struct net_device *dev)
dev_hold(dev);
queue_work(vxlan_wq, &vxlan->sock_work);
}
- spin_unlock(&vn->sock_lock);
+ spin_unlock(&vn->vxlan_list_lock);
return 0;
}
@@ -2188,32 +2120,6 @@ static struct device_type vxlan_type = {
.name = "vxlan",
};
-/* Calls the ndo_add_vxlan_port of the caller in order to
- * 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)
-{
- struct vxlan_sock *vs;
- struct net *net = dev_net(dev);
- struct vxlan_net *vn = net_generic(net, vxlan_net_id);
- sa_family_t sa_family;
- __be16 port;
- unsigned int i;
-
- spin_lock(&vn->sock_lock);
- for (i = 0; i < PORT_HASH_SIZE; ++i) {
- 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);
- }
- }
- spin_unlock(&vn->sock_lock);
-}
-EXPORT_SYMBOL_GPL(vxlan_get_rx_port);
-
/* Initialize the device structure. */
static void vxlan_setup(struct net_device *dev)
{
@@ -2335,59 +2241,44 @@ static const struct ethtool_ops vxlan_ethtool_ops = {
static void vxlan_del_work(struct work_struct *work)
{
struct vxlan_sock *vs = container_of(work, struct vxlan_sock, del_work);
-
- sk_release_kernel(vs->sock->sk);
+ sk_release_kernel(vs->uts.sock->sk);
kfree_rcu(vs, rcu);
}
-static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
- __be16 port, u32 flags)
+/* Create new listen socket if needed */
+static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
+ vxlan_rcv_t rcv, void *data,
+ u32 flags)
{
- struct socket *sock;
- struct udp_port_cfg udp_conf;
- int err;
+ bool ipv6 = !!(flags & VXLAN_F_IPV6);
+ struct vxlan_sock *vs;
+ struct udp_tunnel_socket_cfg vxlan_ts_cfg;
+ unsigned int h;
- memset(&udp_conf, 0, sizeof(udp_conf));
+ memset(&vxlan_ts_cfg, 0, sizeof(struct udp_tunnel_socket_cfg));
if (ipv6) {
- udp_conf.family = AF_INET6;
- udp_conf.use_udp6_tx_checksums =
+ vxlan_ts_cfg.port.family = AF_INET6;
+ vxlan_ts_cfg.port.use_udp6_tx_checksums =
!!(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
- udp_conf.use_udp6_rx_checksums =
+ vxlan_ts_cfg.port.use_udp6_rx_checksums =
!!(flags & VXLAN_F_UDP_ZERO_CSUM6_RX);
} else {
- udp_conf.family = AF_INET;
- udp_conf.local_ip.s_addr = INADDR_ANY;
- udp_conf.use_udp_checksums =
+ vxlan_ts_cfg.port.family = AF_INET;
+ vxlan_ts_cfg.port.local_ip.s_addr = INADDR_ANY;
+ vxlan_ts_cfg.port.use_udp_checksums =
!!(flags & VXLAN_F_UDP_CSUM);
}
- udp_conf.local_udp_port = port;
-
- /* Open UDP socket */
- err = udp_sock_create(net, &udp_conf, &sock);
- if (err < 0)
- return ERR_PTR(err);
-
- /* Disable multicast loopback */
- inet_sk(sock->sk)->mc_loop = 0;
-
- 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,
- u32 flags)
-{
- struct vxlan_net *vn = net_generic(net, vxlan_net_id);
- struct vxlan_sock *vs;
- struct socket *sock;
- struct sock *sk;
- unsigned int h;
- bool ipv6 = !!(flags & VXLAN_F_IPV6);
+ vxlan_ts_cfg.port.local_udp_port = port;
+ vxlan_ts_cfg.encap_type = 1;
+ vxlan_ts_cfg.encap_rcv = vxlan_udp_encap_recv;
+ vxlan_ts_cfg.encap_destroy = NULL;
+ vxlan_ts_cfg.protocol_bit = NETIF_F_RX_UT_VXLAN;
- vs = kzalloc(sizeof(*vs), GFP_KERNEL);
+ vs = (struct vxlan_sock *)create_udp_tunnel_sock(net, sizeof(*vs),
+ NULL,
+ &vxlan_ts_cfg);
if (!vs)
return ERR_PTR(-ENOMEM);
@@ -2396,47 +2287,25 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
INIT_WORK(&vs->del_work, vxlan_del_work);
- sock = vxlan_create_sock(net, ipv6, port, flags);
- if (IS_ERR(sock)) {
- kfree(vs);
- return ERR_CAST(sock);
- }
-
- vs->sock = sock;
- sk = sock->sk;
atomic_set(&vs->refcnt, 1);
+
vs->rcv = rcv;
- vs->data = data;
- rcu_assign_sk_user_data(vs->sock->sk, vs);
+ vs->rcv_data = data;
/* 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(vs);
- spin_unlock(&vn->sock_lock);
-
- /* Mark socket as an encapsulation socket. */
- udp_sk(sk)->encap_type = 1;
- udp_sk(sk)->encap_rcv = vxlan_udp_encap_recv;
-#if IS_ENABLED(CONFIG_IPV6)
- if (ipv6)
- ipv6_stub->udpv6_encap_enable();
- else
-#endif
- udp_encap_enable();
return vs;
}
struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
- vxlan_rcv_t *rcv, void *data,
+ vxlan_rcv_t rcv, void *data,
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, flags);
@@ -2446,7 +2315,6 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
if (no_share) /* Return error if sharing is not allowed. */
return vs;
- spin_lock(&vn->sock_lock);
vs = vxlan_find_sock(net, port);
if (vs) {
if (vs->rcv == rcv)
@@ -2454,7 +2322,6 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
else
vs = ERR_PTR(-EBUSY);
}
- spin_unlock(&vn->sock_lock);
if (!vs)
vs = ERR_PTR(-EINVAL);
@@ -2473,10 +2340,10 @@ static void vxlan_sock_work(struct work_struct *work)
struct vxlan_sock *nvs;
nvs = vxlan_sock_add(net, port, vxlan_rcv, NULL, false, vxlan->flags);
- spin_lock(&vn->sock_lock);
+ spin_lock(&vn->vxlan_list_lock);
if (!IS_ERR(nvs))
vxlan_vs_add_dev(nvs, vxlan);
- spin_unlock(&vn->sock_lock);
+ spin_unlock(&vn->vxlan_list_lock);
dev_put(vxlan->dev);
}
@@ -2643,10 +2510,10 @@ static void vxlan_dellink(struct net_device *dev, struct list_head *head)
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
- spin_lock(&vn->sock_lock);
+ spin_lock(&vn->vxlan_list_lock);
if (!hlist_unhashed(&vxlan->hlist))
hlist_del_rcu(&vxlan->hlist);
- spin_unlock(&vn->sock_lock);
+ spin_unlock(&vn->vxlan_list_lock);
list_del(&vxlan->next);
unregister_netdevice_queue(dev, head);
@@ -2804,13 +2671,9 @@ static struct notifier_block vxlan_notifier_block __read_mostly = {
static __net_init int vxlan_init_net(struct net *net)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
- unsigned int h;
INIT_LIST_HEAD(&vn->vxlan_list);
- spin_lock_init(&vn->sock_lock);
-
- for (h = 0; h < PORT_HASH_SIZE; ++h)
- INIT_HLIST_HEAD(&vn->sock_list[h]);
+ spin_lock_init(&vn->vxlan_list_lock);
return 0;
}
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3837739..41d0ad0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -966,18 +966,22 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
* not implement this, it is assumed that the hw is not able to have
* multiple net devices on single physical port.
*
- * void (*ndo_add_vxlan_port)(struct net_device *dev,
- * sa_family_t sa_family, __be16 port);
- * Called by vxlan to notiy a driver about the UDP port and socket
- * address family that vxlan is listnening to. It is called only when
- * a new port starts listening. The operation is protected by the
- * vxlan_net->sock_lock.
- *
- * void (*ndo_del_vxlan_port)(struct net_device *dev,
- * sa_family_t sa_family, __be16 port);
- * Called by vxlan to notify the driver about a UDP port and socket
- * address family that vxlan is not listening to anymore. The operation
- * is protected by the vxlan_net->sock_lock.
+ * void (*ndo_add_udp_tunnel_port)(struct net_device *dev,
+ * sa_family_t sa_family, __be16 port,
+ * u64 protocol_bit);
+ * Called by a UDP based tunnel protocol to notiy a driver about the UDP
+ * port and socket address family that the UDP tunnel protocol is
+ * listnening to. It is called only when a new port starts listening.
+ * protocol_bit is one of NETIF_F_RX_UT_ fields. The operation is
+ * protected by the udp_tunnel_net->sock_lock.
+ *
+ * void (*ndo_del_udp_tunnel_port)(struct net_device *dev,
+ * sa_family_t sa_family, __be16 port,
+ * u64 protocol_bit);
+ * Called by a UDP based tunnel protocol to notify the driver about a
+ * UDP port and socket address family that the UDP tunnel protocol is
+ * not listening to anymore. protocol_bit is one of the NETIF_F_RX_UT_
+ * fields. The operation is protected by the udp_tunnel_net->sock_lock.
*
* void* (*ndo_dfwd_add_station)(struct net_device *pdev,
* struct net_device *dev)
@@ -1130,13 +1134,14 @@ struct net_device_ops {
bool new_carrier);
int (*ndo_get_phys_port_id)(struct net_device *dev,
struct netdev_phys_port_id *ppid);
- void (*ndo_add_vxlan_port)(struct net_device *dev,
- sa_family_t sa_family,
- __be16 port);
- void (*ndo_del_vxlan_port)(struct net_device *dev,
- sa_family_t sa_family,
- __be16 port);
-
+ void (*ndo_add_udp_tunnel_port)(
+ struct net_device *dev,
+ sa_family_t sa_family, __be16 port,
+ u64 protocol_bit);
+ void (*ndo_del_udp_tunnel_port)(
+ struct net_device *dev,
+ sa_family_t sa_family, __be16 port,
+ u64 protocol_bit);
void* (*ndo_dfwd_add_station)(struct net_device *pdev,
struct net_device *dev);
void (*ndo_dfwd_del_station)(struct net_device *pdev,
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index d5f59f3..50e98f4 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -4,23 +4,25 @@
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/udp.h>
+#include <net/udp_tunnel.h>
#define VNI_HASH_BITS 10
#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
struct vxlan_sock;
-typedef void (vxlan_rcv_t)(struct vxlan_sock *vh, struct sk_buff *skb, __be32 key);
-/* per UDP socket information */
+typedef void (*vxlan_rcv_t)(struct vxlan_sock *vs, struct sk_buff *skb,
+ __be32 key);
+
+/* per vxlan socket information */
struct vxlan_sock {
- struct hlist_node hlist;
- vxlan_rcv_t *rcv;
- void *data;
+ struct udp_tunnel_sock uts; /* Must be the first member */
struct work_struct del_work;
- struct socket *sock;
struct rcu_head rcu;
struct hlist_head vni_list[VNI_HASH_SIZE];
atomic_t refcnt;
+ vxlan_rcv_t rcv;
+ void *rcv_data;
struct udp_offload udp_offloads;
};
@@ -35,7 +37,7 @@ struct vxlan_sock {
#define VXLAN_F_UDP_ZERO_CSUM6_RX 0x100
struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
- vxlan_rcv_t *rcv, void *data,
+ vxlan_rcv_t rcv, void *data,
bool no_share, u32 flags);
void vxlan_sock_release(struct vxlan_sock *vs);
@@ -50,11 +52,4 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
/* IPv6 header + UDP + VXLAN + Ethernet header */
#define VXLAN6_HEADROOM (40 + 8 + 8 + 14)
-#if IS_ENABLED(CONFIG_VXLAN)
-void vxlan_get_rx_port(struct net_device *netdev);
-#else
-static inline void vxlan_get_rx_port(struct net_device *netdev)
-{
-}
-#endif
#endif
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 8d22ecd..cc8b91c 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -326,10 +326,14 @@ void udp_tunnel_get_rx_port(struct net_device *dev)
spin_lock(&utn->sock_lock);
for (i = 0; i < PORT_HASH_SIZE; ++i) {
hlist_for_each_entry_rcu(uts, &utn->sock_list[i], hlist) {
+ if (!(dev->features & uts->protocol_bit))
+ continue;
+
port = inet_sk(uts->sock->sk)->inet_sport;
sa_family = uts->sock->sk->sk_family;
- dev->netdev_ops->ndo_add_vxlan_port(dev, sa_family,
- port);
+
+ dev->netdev_ops->ndo_add_udp_tunnel_port(dev,
+ sa_family, port, uts->protocol_bit);
}
}
spin_unlock(&utn->sock_lock);
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index d8b7e24..7599efd 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -59,7 +59,7 @@ static inline struct vxlan_port *vxlan_vport(const struct vport *vport)
static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
{
struct ovs_key_ipv4_tunnel tun_key;
- struct vport *vport = vs->data;
+ struct vport *vport = vs->rcv_data;
struct iphdr *iph;
__be64 key;
@@ -74,7 +74,7 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb)
{
struct vxlan_port *vxlan_port = vxlan_vport(vport);
- __be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
+ __be16 dst_port = inet_sk(vxlan_port->vs->uts.sock->sk)->inet_sport;
if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port)))
return -EMSGSIZE;
@@ -139,7 +139,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
{
struct net *net = ovs_dp_get_net(vport->dp);
struct vxlan_port *vxlan_port = vxlan_vport(vport);
- __be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
+ __be16 dst_port = inet_sk(vxlan_port->vs->uts.sock->sk)->inet_sport;
struct rtable *rt;
struct flowi4 fl;
__be16 src_port;
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists