vxlan: Eliminate dependency on UDP socket in transmit path

In the vxlan transmit path there is no need to reference the socket
for a tunnel which is needed for the receive side. We do, however,
need the vxlan_dev flags. This patch eliminate references
to the socket in the transmit path, and changes VXLAN_F_UNSHAREABLE
to be VXLAN_F_RCV_FLAGS. This mask is used to store the flags
applicable to receive (GBP, CSUM6_RX, and REMCSUM_RX) in the
vxlan_sock flags.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index a288ceab502e78b7d6f5d60b904d445342c9b734..87736e65cd158d239f64c917cf102ba9d8dcba0b 100644 (file)
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -270,12 +270,13 @@ static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family,
                                          __be16 port, u32 flags)
 {
        struct vxlan_sock *vs;
-       u32 match_flags = flags & VXLAN_F_UNSHAREABLE;
+
+       flags &= VXLAN_F_RCV_FLAGS;
 
        hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) {
                if (inet_sk(vs->sock->sk)->inet_sport == port &&
                    inet_sk(vs->sock->sk)->sk.sk_family == family &&
-                   (vs->flags & VXLAN_F_UNSHAREABLE) == match_flags)
+                   vs->flags == flags)
                        return vs;
        }
        return NULL;
@@ -1674,7 +1675,7 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
        return false;
 }
 
-static void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, struct vxlan_sock *vs,
+static void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, u32 vxflags,
                                struct vxlan_metadata *md)
 {
        struct vxlanhdr_gbp *gbp;
@@ -1692,21 +1693,20 @@ static void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, struct vxlan_sock *vs,
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static int vxlan6_xmit_skb(struct vxlan_sock *vs,
-                          struct dst_entry *dst, struct sk_buff *skb,
+static int vxlan6_xmit_skb(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,
-                          struct vxlan_metadata *md, bool xnet)
+                          struct vxlan_metadata *md, bool xnet, u32 vxflags)
 {
        struct vxlanhdr *vxh;
        int min_headroom;
        int err;
-       bool udp_sum = !udp_get_no_check6_tx(vs->sock->sk);
+       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 ((vs->flags & VXLAN_F_REMCSUM_TX) &&
+       if ((vxflags & VXLAN_F_REMCSUM_TX) &&
            skb->ip_summed == CHECKSUM_PARTIAL) {
                int csum_start = skb_checksum_start_offset(skb);
 
@@ -1764,14 +1764,14 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
                }
        }
 
-       if (vs->flags & VXLAN_F_GBP)
-               vxlan_build_gbp_hdr(vxh, vs, md);
+       if (vxflags & VXLAN_F_GBP)
+               vxlan_build_gbp_hdr(vxh, vxflags, md);
 
        skb_set_inner_protocol(skb, htons(ETH_P_TEB));
 
        udp_tunnel6_xmit_skb(dst, skb, dev, saddr, daddr, prio,
                             ttl, src_port, dst_port,
-                            udp_get_no_check6_tx(vs->sock->sk));
+                            !!(vxflags & VXLAN_F_UDP_ZERO_CSUM6_TX));
        return 0;
 err:
        dst_release(dst);
@@ -1779,20 +1779,19 @@ err:
 }
 #endif
 
-int vxlan_xmit_skb(struct vxlan_sock *vs,
-                  struct rtable *rt, struct sk_buff *skb,
+int vxlan_xmit_skb(struct rtable *rt, struct sk_buff *skb,
                   __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
                   __be16 src_port, __be16 dst_port,
-                  struct vxlan_metadata *md, bool xnet)
+                  struct vxlan_metadata *md, bool xnet, u32 vxflags)
 {
        struct vxlanhdr *vxh;
        int min_headroom;
        int err;
-       bool udp_sum = !vs->sock->sk->sk_no_check_tx;
+       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 ((vs->flags & VXLAN_F_REMCSUM_TX) &&
+       if ((vxflags & VXLAN_F_REMCSUM_TX) &&
            skb->ip_summed == CHECKSUM_PARTIAL) {
                int csum_start = skb_checksum_start_offset(skb);
 
@@ -1844,14 +1843,14 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
                }
        }
 
-       if (vs->flags & VXLAN_F_GBP)
-               vxlan_build_gbp_hdr(vxh, vs, md);
+       if (vxflags & VXLAN_F_GBP)
+               vxlan_build_gbp_hdr(vxh, vxflags, md);
 
        skb_set_inner_protocol(skb, htons(ETH_P_TEB));
 
        return udp_tunnel_xmit_skb(rt, skb, src, dst, tos,
                                   ttl, df, src_port, dst_port, xnet,
-                                  vs->sock->sk->sk_no_check_tx);
+                                  !(vxflags & VXLAN_F_UDP_CSUM));
 }
 EXPORT_SYMBOL_GPL(vxlan_xmit_skb);
 
@@ -1983,10 +1982,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
                md.vni = htonl(vni << 8);
                md.gbp = skb->mark;
 
-               err = vxlan_xmit_skb(vxlan->vn_sock, rt, skb,
-                                    fl4.saddr, dst->sin.sin_addr.s_addr,
-                                    tos, ttl, df, src_port, dst_port, &md,
-                                    !net_eq(vxlan->net, dev_net(vxlan->dev)));
+               err = vxlan_xmit_skb(rt, skb, fl4.saddr,
+                                    dst->sin.sin_addr.s_addr, tos, ttl, df,
+                                    src_port, dst_port, &md,
+                                    !net_eq(vxlan->net, dev_net(vxlan->dev)),
+                                    vxlan->flags);
                if (err < 0) {
                        /* skb is already freed. */
                        skb = NULL;
@@ -2042,10 +2042,10 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
                md.vni = htonl(vni << 8);
                md.gbp = skb->mark;
 
-               err = vxlan6_xmit_skb(vxlan->vn_sock, ndst, skb,
-                                     dev, &fl6.saddr, &fl6.daddr, 0, ttl,
-                                     src_port, dst_port, &md,
-                                     !net_eq(vxlan->net, dev_net(vxlan->dev)));
+               err = vxlan6_xmit_skb(ndst, skb, dev, &fl6.saddr, &fl6.daddr,
+                                     0, ttl, src_port, dst_port, &md,
+                                     !net_eq(vxlan->net, dev_net(vxlan->dev)),
+                                     vxlan->flags);
 #endif
        }
 
@@ -2517,15 +2517,11 @@ static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
 
        if (ipv6) {
                udp_conf.family = AF_INET6;
-               udp_conf.use_udp6_tx_checksums =
-                   !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
                udp_conf.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 =
-                   !!(flags & VXLAN_F_UDP_CSUM);
        }
 
        udp_conf.local_udp_port = port;
@@ -2569,7 +2565,7 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
        atomic_set(&vs->refcnt, 1);
        vs->rcv = rcv;
        vs->data = data;
-       vs->flags = flags;
+       vs->flags = (flags & VXLAN_F_RCV_FLAGS);
 
        /* Initialize the vxlan udp offloads structure */
        vs->udp_offloads.port = port;

diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 7be8c342fc95f42288f225083e925ff3a05a8882..2927d6244481ae24092ba829f857e57fffcaacfd 100644 (file)
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -129,8 +129,12 @@ struct vxlan_sock {
 #define VXLAN_F_REMCSUM_RX             0x400
 #define VXLAN_F_GBP                    0x800
 
-/* These flags must match in order for a socket to be shareable */
-#define VXLAN_F_UNSHAREABLE            VXLAN_F_GBP
+/* Flags that are used in the receive patch. These flags must match in
+ * order for a socket to be shareable
+ */
+#define VXLAN_F_RCV_FLAGS              (VXLAN_F_GBP |                  \
+                                        VXLAN_F_UDP_ZERO_CSUM6_RX |    \
+                                        VXLAN_F_REMCSUM_RX)
 
 struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
                                  vxlan_rcv_t *rcv, void *data,
@@ -138,11 +142,10 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 
 void vxlan_sock_release(struct vxlan_sock *vs);
 
-int vxlan_xmit_skb(struct vxlan_sock *vs,
-                  struct rtable *rt, struct sk_buff *skb,
+int vxlan_xmit_skb(struct rtable *rt, struct sk_buff *skb,
                   __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
                   __be16 src_port, __be16 dst_port, struct vxlan_metadata *md,
-                  bool xnet);
+                  bool xnet, u32 vxflags);
 
 static inline netdev_features_t vxlan_features_check(struct sk_buff *skb,
                                                     netdev_features_t features)

diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 8a2d54cba9ba9614d4da4082af175425b6537cd4..3cc983bf444af4ba98225793eed8f04365f33ca3 100644 (file)
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -252,12 +252,10 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
        md.vni = htonl(be64_to_cpu(tun_key->tun_id) << 8);
        md.gbp = vxlan_ext_gbp(skb);
 
-       err = vxlan_xmit_skb(vxlan_port->vs, rt, skb,
-                            fl.saddr, tun_key->ipv4_dst,
+       err = vxlan_xmit_skb(rt, skb, fl.saddr, tun_key->ipv4_dst,
                             tun_key->ipv4_tos, tun_key->ipv4_ttl, df,
                             src_port, dst_port,
-                            &md,
-                            false);
+                            &md, false, vxlan_port->exts);
        if (err < 0)
                ip_rt_put(rt);
        return err;