summaryrefslogtreecommitdiff
path: root/net/openvswitch
diff options
context:
space:
mode:
Diffstat (limited to 'net/openvswitch')
-rw-r--r--net/openvswitch/actions.c129
-rw-r--r--net/openvswitch/conntrack.c8
-rw-r--r--net/openvswitch/datapath.c35
-rw-r--r--net/openvswitch/datapath.h2
-rw-r--r--net/openvswitch/flow.c105
-rw-r--r--net/openvswitch/flow.h22
-rw-r--r--net/openvswitch/flow_netlink.c179
-rw-r--r--net/openvswitch/vport-internal_dev.c10
-rw-r--r--net/openvswitch/vport-netdev.c10
-rw-r--r--net/openvswitch/vport.c48
-rw-r--r--net/openvswitch/vport.h3
11 files changed, 368 insertions, 183 deletions
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 4e03f64709bc..514f7bcf7c63 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -62,9 +62,11 @@ struct ovs_frag_data {
struct vport *vport;
struct ovs_skb_cb cb;
__be16 inner_protocol;
- __u16 vlan_tci;
+ u16 network_offset; /* valid only for MPLS */
+ u16 vlan_tci;
__be16 vlan_proto;
unsigned int l2_len;
+ u8 mac_proto;
u8 l2_data[MAX_L2_LEN];
};
@@ -136,12 +138,12 @@ static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
static void invalidate_flow_key(struct sw_flow_key *key)
{
- key->eth.type = htons(0);
+ key->mac_proto |= SW_FLOW_KEY_INVALID;
}
static bool is_flow_key_valid(const struct sw_flow_key *key)
{
- return !!key->eth.type;
+ return !(key->mac_proto & SW_FLOW_KEY_INVALID);
}
static void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr,
@@ -185,7 +187,8 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN);
- update_ethertype(skb, eth_hdr(skb), mpls->mpls_ethertype);
+ if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET)
+ update_ethertype(skb, eth_hdr(skb), mpls->mpls_ethertype);
skb->protocol = mpls->mpls_ethertype;
invalidate_flow_key(key);
@@ -195,7 +198,6 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
const __be16 ethertype)
{
- struct ethhdr *hdr;
int err;
err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
@@ -211,11 +213,15 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb->mac_len);
- /* mpls_hdr() is used to locate the ethertype field correctly in the
- * presence of VLAN tags.
- */
- hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN);
- update_ethertype(skb, hdr, ethertype);
+ if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET) {
+ struct ethhdr *hdr;
+
+ /* mpls_hdr() is used to locate the ethertype field correctly in the
+ * presence of VLAN tags.
+ */
+ hdr = (struct ethhdr *)((void *)mpls_hdr(skb) - ETH_HLEN);
+ update_ethertype(skb, hdr, ethertype);
+ }
if (eth_p_mpls(skb->protocol))
skb->protocol = ethertype;
@@ -311,6 +317,47 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
return 0;
}
+/* pop_eth does not support VLAN packets as this action is never called
+ * for them.
+ */
+static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
+{
+ skb_pull_rcsum(skb, ETH_HLEN);
+ skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);
+
+ /* safe right before invalidate_flow_key */
+ key->mac_proto = MAC_PROTO_NONE;
+ invalidate_flow_key(key);
+ return 0;
+}
+
+static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,
+ const struct ovs_action_push_eth *ethh)
+{
+ struct ethhdr *hdr;
+
+ /* Add the new Ethernet header */
+ if (skb_cow_head(skb, ETH_HLEN) < 0)
+ return -ENOMEM;
+
+ skb_push(skb, ETH_HLEN);
+ skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);
+
+ hdr = eth_hdr(skb);
+ ether_addr_copy(hdr->h_source, ethh->addresses.eth_src);
+ ether_addr_copy(hdr->h_dest, ethh->addresses.eth_dst);
+ hdr->h_proto = skb->protocol;
+
+ skb_postpush_rcsum(skb, hdr, ETH_HLEN);
+
+ /* safe right before invalidate_flow_key */
+ key->mac_proto = MAC_PROTO_ETHERNET;
+ invalidate_flow_key(key);
+ return 0;
+}
+
static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh,
__be32 addr, __be32 new_addr)
{
@@ -666,7 +713,13 @@ static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *sk
skb_postpush_rcsum(skb, skb->data, data->l2_len);
skb_reset_mac_header(skb);
- ovs_vport_send(vport, skb);
+ if (eth_p_mpls(skb->protocol)) {
+ skb->inner_network_header = skb->network_header;
+ skb_set_network_header(skb, data->network_offset);
+ skb_reset_mac_len(skb);
+ }
+
+ ovs_vport_send(vport, skb, data->mac_proto);
return 0;
}
@@ -684,7 +737,8 @@ static struct dst_ops ovs_dst_ops = {
/* prepare_frag() is called once per (larger-than-MTU) frame; its inverse is
* ovs_vport_output(), which is called once per fragmented packet.
*/
-static void prepare_frag(struct vport *vport, struct sk_buff *skb)
+static void prepare_frag(struct vport *vport, struct sk_buff *skb,
+ u16 orig_network_offset, u8 mac_proto)
{
unsigned int hlen = skb_network_offset(skb);
struct ovs_frag_data *data;
@@ -694,8 +748,10 @@ static void prepare_frag(struct vport *vport, struct sk_buff *skb)
data->vport = vport;
data->cb = *OVS_CB(skb);
data->inner_protocol = skb->inner_protocol;
+ data->network_offset = orig_network_offset;
data->vlan_tci = skb->vlan_tci;
data->vlan_proto = skb->vlan_proto;
+ data->mac_proto = mac_proto;
data->l2_len = hlen;
memcpy(&data->l2_data, skb->data, hlen);
@@ -704,18 +760,27 @@ static void prepare_frag(struct vport *vport, struct sk_buff *skb)
}
static void ovs_fragment(struct net *net, struct vport *vport,
- struct sk_buff *skb, u16 mru, __be16 ethertype)
+ struct sk_buff *skb, u16 mru,
+ struct sw_flow_key *key)
{
+ u16 orig_network_offset = 0;
+
+ if (eth_p_mpls(skb->protocol)) {
+ orig_network_offset = skb_network_offset(skb);
+ skb->network_header = skb->inner_network_header;
+ }
+
if (skb_network_offset(skb) > MAX_L2_LEN) {
OVS_NLERR(1, "L2 header too long to fragment");
goto err;
}
- if (ethertype == htons(ETH_P_IP)) {
+ if (key->eth.type == htons(ETH_P_IP)) {
struct dst_entry ovs_dst;
unsigned long orig_dst;
- prepare_frag(vport, skb);
+ prepare_frag(vport, skb, orig_network_offset,
+ ovs_key_mac_proto(key));
dst_init(&ovs_dst, &ovs_dst_ops, NULL, 1,
DST_OBSOLETE_NONE, DST_NOCOUNT);
ovs_dst.dev = vport->dev;
@@ -726,7 +791,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
ip_do_fragment(net, skb->sk, skb, ovs_vport_output);
refdst_drop(orig_dst);
- } else if (ethertype == htons(ETH_P_IPV6)) {
+ } else if (key->eth.type == htons(ETH_P_IPV6)) {
const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
unsigned long orig_dst;
struct rt6_info ovs_rt;
@@ -735,7 +800,8 @@ static void ovs_fragment(struct net *net, struct vport *vport,
goto err;
}
- prepare_frag(vport, skb);
+ prepare_frag(vport, skb, orig_network_offset,
+ ovs_key_mac_proto(key));
memset(&ovs_rt, 0, sizeof(ovs_rt));
dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL, 1,
DST_OBSOLETE_NONE, DST_NOCOUNT);
@@ -749,7 +815,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
refdst_drop(orig_dst);
} else {
WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
- ovs_vport_name(vport), ntohs(ethertype), mru,
+ ovs_vport_name(vport), ntohs(key->eth.type), mru,
vport->dev->mtu);
goto err;
}
@@ -769,26 +835,19 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
u32 cutlen = OVS_CB(skb)->cutlen;
if (unlikely(cutlen > 0)) {
- if (skb->len - cutlen > ETH_HLEN)
+ if (skb->len - cutlen > ovs_mac_header_len(key))
pskb_trim(skb, skb->len - cutlen);
else
- pskb_trim(skb, ETH_HLEN);
+ pskb_trim(skb, ovs_mac_header_len(key));
}
- if (likely(!mru || (skb->len <= mru + ETH_HLEN))) {
- ovs_vport_send(vport, skb);
+ if (likely(!mru ||
+ (skb->len <= mru + vport->dev->hard_header_len))) {
+ ovs_vport_send(vport, skb, ovs_key_mac_proto(key));
} else if (mru <= vport->dev->mtu) {
struct net *net = read_pnet(&dp->net);
- __be16 ethertype = key->eth.type;
-
- if (!is_flow_key_valid(key)) {
- if (eth_p_mpls(skb->protocol))
- ethertype = skb->inner_protocol;
- else
- ethertype = vlan_get_protocol(skb);
- }
- ovs_fragment(net, vport, skb, mru, ethertype);
+ ovs_fragment(net, vport, skb, mru, key);
} else {
kfree_skb(skb);
}
@@ -1182,6 +1241,14 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
if (err)
return err == -EINPROGRESS ? 0 : err;
break;
+
+ case OVS_ACTION_ATTR_PUSH_ETH:
+ err = push_eth(skb, key, nla_data(a));
+ break;
+
+ case OVS_ACTION_ATTR_POP_ETH:
+ err = pop_eth(skb, key);
+ break;
}
if (unlikely(err)) {
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index fecefa2dc94e..6b78bab27755 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -728,12 +728,8 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
skb->nfctinfo = IP_CT_NEW;
}
- /* Repeat if requested, see nf_iterate(). */
- do {
- err = nf_conntrack_in(net, info->family,
- NF_INET_PRE_ROUTING, skb);
- } while (err == NF_REPEAT);
-
+ err = nf_conntrack_in(net, info->family,
+ NF_INET_PRE_ROUTING, skb);
if (err != NF_ACCEPT)
return -ENOENT;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 4d67ea856067..2d4c4d3911c0 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -58,8 +58,7 @@
#include "vport-internal_dev.h"
#include "vport-netdev.h"
-int ovs_net_id __read_mostly;
-EXPORT_SYMBOL_GPL(ovs_net_id);
+unsigned int ovs_net_id __read_mostly;
static struct genl_family dp_packet_genl_family;
static struct genl_family dp_flow_genl_family;
@@ -131,7 +130,6 @@ int lockdep_ovsl_is_held(void)
else
return 1;
}
-EXPORT_SYMBOL_GPL(lockdep_ovsl_is_held);
#endif
static struct vport *new_vport(const struct vport_parms *);
@@ -562,7 +560,6 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
struct sw_flow *flow;
struct sw_flow_actions *sf_acts;
struct datapath *dp;
- struct ethhdr *eth;
struct vport *input_vport;
u16 mru = 0;
int len;
@@ -583,17 +580,6 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
nla_memcpy(__skb_put(packet, len), a[OVS_PACKET_ATTR_PACKET], len);
- skb_reset_mac_header(packet);
- eth = eth_hdr(packet);
-
- /* Normally, setting the skb 'protocol' field would be handled by a
- * call to eth_type_trans(), but it assumes there's a sending
- * device, which we may not have. */
- if (eth_proto_is_802_3(eth->h_proto))
- packet->protocol = eth->h_proto;
- else
- packet->protocol = htons(ETH_P_802_2);
-
/* Set packet's mru */
if (a[OVS_PACKET_ATTR_MRU]) {
mru = nla_get_u16(a[OVS_PACKET_ATTR_MRU]);
@@ -620,6 +606,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
rcu_assign_pointer(flow->sf_acts, acts);
packet->priority = flow->key.phy.priority;
packet->mark = flow->key.phy.skb_mark;
+ packet->protocol = flow->key.eth.type;
rcu_read_lock();
dp = get_dp_rcu(net, ovs_header->dp_ifindex);
@@ -672,8 +659,7 @@ static const struct genl_ops dp_packet_genl_ops[] = {
}
};
-static struct genl_family dp_packet_genl_family = {
- .id = GENL_ID_GENERATE,
+static struct genl_family dp_packet_genl_family __ro_after_init = {
.hdrsize = sizeof(struct ovs_header),
.name = OVS_PACKET_FAMILY,
.version = OVS_PACKET_VERSION,
@@ -682,6 +668,7 @@ static struct genl_family dp_packet_genl_family = {
.parallel_ops = true,
.ops = dp_packet_genl_ops,
.n_ops = ARRAY_SIZE(dp_packet_genl_ops),
+ .module = THIS_MODULE,
};
static void get_dp_stats(const struct datapath *dp, struct ovs_dp_stats *stats,
@@ -1437,8 +1424,7 @@ static const struct genl_ops dp_flow_genl_ops[] = {
},
};
-static struct genl_family dp_flow_genl_family = {
- .id = GENL_ID_GENERATE,
+static struct genl_family dp_flow_genl_family __ro_after_init = {
.hdrsize = sizeof(struct ovs_header),
.name = OVS_FLOW_FAMILY,
.version = OVS_FLOW_VERSION,
@@ -1449,6 +1435,7 @@ static struct genl_family dp_flow_genl_family = {
.n_ops = ARRAY_SIZE(dp_flow_genl_ops),
.mcgrps = &ovs_dp_flow_multicast_group,
.n_mcgrps = 1,
+ .module = THIS_MODULE,
};
static size_t ovs_dp_cmd_msg_size(void)
@@ -1823,8 +1810,7 @@ static const struct genl_ops dp_datapath_genl_ops[] = {
},
};
-static struct genl_family dp_datapath_genl_family = {
- .id = GENL_ID_GENERATE,
+static struct genl_family dp_datapath_genl_family __ro_after_init = {
.hdrsize = sizeof(struct ovs_header),
.name = OVS_DATAPATH_FAMILY,
.version = OVS_DATAPATH_VERSION,
@@ -1835,6 +1821,7 @@ static struct genl_family dp_datapath_genl_family = {
.n_ops = ARRAY_SIZE(dp_datapath_genl_ops),
.mcgrps = &ovs_dp_datapath_multicast_group,
.n_mcgrps = 1,
+ .module = THIS_MODULE,
};
/* Called with ovs_mutex or RCU read lock. */
@@ -2245,8 +2232,7 @@ static const struct genl_ops dp_vport_genl_ops[] = {
},
};
-struct genl_family dp_vport_genl_family = {
- .id = GENL_ID_GENERATE,
+struct genl_family dp_vport_genl_family __ro_after_init = {
.hdrsize = sizeof(struct ovs_header),
.name = OVS_VPORT_FAMILY,
.version = OVS_VPORT_VERSION,
@@ -2257,6 +2243,7 @@ struct genl_family dp_vport_genl_family = {
.n_ops = ARRAY_SIZE(dp_vport_genl_ops),
.mcgrps = &ovs_dp_vport_multicast_group,
.n_mcgrps = 1,
+ .module = THIS_MODULE,
};
static struct genl_family * const dp_genl_families[] = {
@@ -2274,7 +2261,7 @@ static void dp_unregister_genl(int n_families)
genl_unregister_family(dp_genl_families[i]);
}
-static int dp_register_genl(void)
+static int __init dp_register_genl(void)
{
int err;
int i;
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index ab85c1cae255..1c6e9377436d 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -144,7 +144,7 @@ struct ovs_net {
bool xt_label;
};
-extern int ovs_net_id;
+extern unsigned int ovs_net_id;
void ovs_lock(void);
void ovs_unlock(void);
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 22087062bd10..08aa926cd5cf 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -334,14 +334,17 @@ static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh)
return 1;
}
-static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
+static void clear_vlan(struct sw_flow_key *key)
{
- int res;
-
key->eth.vlan.tci = 0;
key->eth.vlan.tpid = 0;
key->eth.cvlan.tci = 0;
key->eth.cvlan.tpid = 0;
+}
+
+static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
+{
+ int res;
if (skb_vlan_tag_present(skb)) {
key->eth.vlan.tci = htons(skb->vlan_tci);
@@ -483,17 +486,20 @@ invalid:
*
* Returns 0 if successful, otherwise a negative errno value.
*
- * Initializes @skb header pointers as follows:
+ * Initializes @skb header fields as follows:
*
- * - skb->mac_header: the Ethernet header.
+ * - skb->mac_header: the L2 header.
*
- * - skb->network_header: just past the Ethernet header, or just past the
- * VLAN header, to the first byte of the Ethernet payload.
+ * - skb->network_header: just past the L2 header, or just past the
+ * VLAN header, to the first byte of the L2 payload.
*
* - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6
* on output, then just past the IP header, if one is present and
* of a correct length, otherwise the same as skb->network_header.
* For other key->eth.type values it is left untouched.
+ *
+ * - skb->protocol: the type of the data starting at skb->network_header.
+ * Equals to key->eth.type.
*/
static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
{
@@ -505,28 +511,35 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
skb_reset_mac_header(skb);
- /* Link layer. We are guaranteed to have at least the 14 byte Ethernet
- * header in the linear data area.
- */
- eth = eth_hdr(skb);
- ether_addr_copy(key->eth.src, eth->h_source);
- ether_addr_copy(key->eth.dst, eth->h_dest);
+ /* Link layer. */
+ clear_vlan(key);
+ if (key->mac_proto == MAC_PROTO_NONE) {
+ if (unlikely(eth_type_vlan(skb->protocol)))
+ return -EINVAL;
- __skb_pull(skb, 2 * ETH_ALEN);
- /* We are going to push all headers that we pull, so no need to
- * update skb->csum here.
- */
+ skb_reset_network_header(skb);
+ } else {
+ eth = eth_hdr(skb);
+ ether_addr_copy(key->eth.src, eth->h_source);
+ ether_addr_copy(key->eth.dst, eth->h_dest);
- if (unlikely(parse_vlan(skb, key)))
- return -ENOMEM;
+ __skb_pull(skb, 2 * ETH_ALEN);
+ /* We are going to push all headers that we pull, so no need to
+ * update skb->csum here.
+ */
- key->eth.type = parse_ethertype(skb);
- if (unlikely(key->eth.type == htons(0)))
- return -ENOMEM;
+ if (unlikely(parse_vlan(skb, key)))
+ return -ENOMEM;
+
+ skb->protocol = parse_ethertype(skb);
+ if (unlikely(skb->protocol == htons(0)))
+ return -ENOMEM;
- skb_reset_network_header(skb);
+ skb_reset_network_header(skb);
+ __skb_push(skb, skb->data - skb_mac_header(skb));
+ }
skb_reset_mac_len(skb);
- __skb_push(skb, skb->data - skb_mac_header(skb));
+ key->eth.type = skb->protocol;
/* Network layer. */
if (key->eth.type == htons(ETH_P_IP)) {
@@ -721,9 +734,25 @@ int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
return key_extract(skb, key);
}
+static int key_extract_mac_proto(struct sk_buff *skb)
+{
+ switch (skb->dev->type) {
+ case ARPHRD_ETHER:
+ return MAC_PROTO_ETHERNET;
+ case ARPHRD_NONE:
+ if (skb->protocol == htons(ETH_P_TEB))
+ return MAC_PROTO_ETHERNET;
+ return MAC_PROTO_NONE;
+ }
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+}
+
int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
struct sk_buff *skb, struct sw_flow_key *key)
{
+ int res;
+
/* Extract metadata from packet. */
if (tun_info) {
key->tun_proto = ip_tunnel_info_af(tun_info);
@@ -751,6 +780,10 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
key->phy.skb_mark = skb->mark;
ovs_ct_fill_key(skb, key);
key->ovs_flow_hash = 0;
+ res = key_extract_mac_proto(skb);
+ if (res < 0)
+ return res;
+ key->mac_proto = res;
key->recirc_id = 0;
return key_extract(skb, key);
@@ -767,5 +800,29 @@ int ovs_flow_key_extract_userspace(struct net *net, const struct nlattr *attr,
if (err)
return err;
+ if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
+ /* key_extract assumes that skb->protocol is set-up for
+ * layer 3 packets which is the case for other callers,
+ * in particular packets recieved from the network stack.
+ * Here the correct value can be set from the metadata
+ * extracted above.
+ */
+ skb->protocol = key->eth.type;
+ } else {
+ struct ethhdr *eth;
+
+ skb_reset_mac_header(skb);
+ eth = eth_hdr(skb);
+
+ /* Normally, setting the skb 'protocol' field would be
+ * handled by a call to eth_type_trans(), but it assumes
+ * there's a sending device, which we may not have.
+ */
+ if (eth_proto_is_802_3(eth->h_proto))
+ skb->protocol = eth->h_proto;
+ else
+ skb->protocol = htons(ETH_P_802_2);
+ }
+
return key_extract(skb, key);
}
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index ae783f5c6695..f61cae7f9030 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -37,6 +37,12 @@
struct sk_buff;
+enum sw_flow_mac_proto {
+ MAC_PROTO_NONE = 0,
+ MAC_PROTO_ETHERNET,
+};
+#define SW_FLOW_KEY_INVALID 0x80
+
/* Store options at the end of the array if they are less than the
* maximum size. This allows us to get the benefits of variable length
* matching for small options.
@@ -68,6 +74,7 @@ struct sw_flow_key {
u32 skb_mark; /* SKB mark. */
u16 in_port; /* Input switch port (or DP_MAX_PORTS). */
} __packed phy; /* Safe when right after 'tun_key'. */
+ u8 mac_proto; /* MAC layer protocol (e.g. Ethernet). */
u8 tun_proto; /* Protocol of encapsulating tunnel. */
u32 ovs_flow_hash; /* Datapath computed hash value. */
u32 recirc_id; /* Recirculation ID. */
@@ -206,6 +213,21 @@ struct arp_eth_header {
unsigned char ar_tip[4]; /* target IP address */
} __packed;
+static inline u8 ovs_key_mac_proto(const struct sw_flow_key *key)
+{
+ return key->mac_proto & ~SW_FLOW_KEY_INVALID;
+}
+
+static inline u16 __ovs_mac_header_len(u8 mac_proto)
+{
+ return mac_proto == MAC_PROTO_ETHERNET ? ETH_HLEN : 0;
+}
+
+static inline u16 ovs_mac_header_len(const struct sw_flow_key *key)
+{
+ return __ovs_mac_header_len(ovs_key_mac_proto(key));
+}
+
static inline bool ovs_identifier_is_ufid(const struct sw_flow_id *sfid)
{
return sfid->ufid_len;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index ae25ded82b3b..d19044f2b1f4 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -123,7 +123,7 @@ static void update_range(struct sw_flow_match *match,
static bool match_validate(const struct sw_flow_match *match,
u64 key_attrs, u64 mask_attrs, bool log)
{
- u64 key_expected = 1 << OVS_KEY_ATTR_ETHERNET;
+ u64 key_expected = 0;
u64 mask_allowed = key_attrs; /* At most allow all key attributes */
/* The following mask attributes allowed only if they
@@ -969,10 +969,33 @@ static int parse_vlan_from_nlattrs(struct sw_flow_match *match,
return 0;
}
+static int parse_eth_type_from_nlattrs(struct sw_flow_match *match,
+ u64 *attrs, const struct nlattr **a,
+ bool is_mask, bool log)
+{
+ __be16 eth_type;
+
+ eth_type = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);
+ if (is_mask) {
+ /* Always exact match EtherType. */
+ eth_type = htons(0xffff);
+ } else if (!eth_proto_is_802_3(eth_type)) {
+ OVS_NLERR(log, "EtherType %x is less than min %x",
+ ntohs(eth_type), ETH_P_802_3_MIN);
+ return -EINVAL;
+ }
+
+ SW_FLOW_KEY_PUT(match, eth.type, eth_type, is_mask);
+ *attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
+ return 0;
+}
+
static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match,
u64 *attrs, const struct nlattr **a,
bool is_mask, bool log)
{
+ u8 mac_proto = MAC_PROTO_ETHERNET;
+
if (*attrs & (1 << OVS_KEY_ATTR_DP_HASH)) {
u32 hash_val = nla_get_u32(a[OVS_KEY_ATTR_DP_HASH]);
@@ -1059,6 +1082,21 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match,
sizeof(*cl), is_mask);
*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABELS);
}
+
+ /* For layer 3 packets the Ethernet type is provided
+ * and treated as metadata but no MAC addresses are provided.
+ */
+ if (!(*attrs & (1ULL << OVS_KEY_ATTR_ETHERNET)) &&
+ (*attrs & (1ULL << OVS_KEY_ATTR_ETHERTYPE)))
+ mac_proto = MAC_PROTO_NONE;
+
+ /* Always exact match mac_proto */
+ SW_FLOW_KEY_PUT(match, mac_proto, is_mask ? 0xff : mac_proto, is_mask);
+
+ if (mac_proto == MAC_PROTO_NONE)
+ return parse_eth_type_from_nlattrs(match, attrs, a, is_mask,
+ log);
+
return 0;
}
@@ -1081,33 +1119,26 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match,
SW_FLOW_KEY_MEMCPY(match, eth.dst,
eth_key->eth_dst, ETH_ALEN, is_mask);
attrs &= ~(1 << OVS_KEY_ATTR_ETHERNET);
- }
- if (attrs & (1 << OVS_KEY_ATTR_VLAN)) {
- /* VLAN attribute is always parsed before getting here since it
- * may occur multiple times.
- */
- OVS_NLERR(log, "VLAN attribute unexpected.");
- return -EINVAL;
- }
-
- if (attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) {
- __be16 eth_type;
-
- eth_type = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);
- if (is_mask) {
- /* Always exact match EtherType. */
- eth_type = htons(0xffff);
- } else if (!eth_proto_is_802_3(eth_type)) {
- OVS_NLERR(log, "EtherType %x is less than min %x",
- ntohs(eth_type), ETH_P_802_3_MIN);
+ if (attrs & (1 << OVS_KEY_ATTR_VLAN)) {
+ /* VLAN attribute is always parsed before getting here since it
+ * may occur multiple times.
+ */
+ OVS_NLERR(log, "VLAN attribute unexpected.");
return -EINVAL;
}
- SW_FLOW_KEY_PUT(match, eth.type, eth_type, is_mask);
- attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
- } else if (!is_mask) {
- SW_FLOW_KEY_PUT(match, eth.type, htons(ETH_P_802_2), is_mask);
+ if (attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) {
+ err = parse_eth_type_from_nlattrs(match, &attrs, a, is_mask,
+ log);
+ if (err)
+ return err;
+ } else if (!is_mask) {
+ SW_FLOW_KEY_PUT(match, eth.type, htons(ETH_P_802_2), is_mask);
+ }
+ } else if (!match->key->eth.type) {
+ OVS_NLERR(log, "Either Ethernet header or EtherType is required.");
+ return -EINVAL;
}
if (attrs & (1 << OVS_KEY_ATTR_IPV4)) {
@@ -1556,42 +1587,44 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
if (ovs_ct_put_key(output, skb))
goto nla_put_failure;
- nla = nla_reserve(skb, OVS_KEY_ATTR_ETHERNET, sizeof(*eth_key));
- if (!nla)
- goto nla_put_failure;
-
- eth_key = nla_data(nla);
- ether_addr_copy(eth_key->eth_src, output->eth.src);
- ether_addr_copy(eth_key->eth_dst, output->eth.dst);
-
- if (swkey->eth.vlan.tci || eth_type_vlan(swkey->eth.type)) {
- if (ovs_nla_put_vlan(skb, &output->eth.vlan, is_mask))
+ if (ovs_key_mac_proto(swkey) == MAC_PROTO_ETHERNET) {
+ nla = nla_reserve(skb, OVS_KEY_ATTR_ETHERNET, sizeof(*eth_key));
+ if (!nla)
goto nla_put_failure;
- encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
- if (!swkey->eth.vlan.tci)
- goto unencap;
- if (swkey->eth.cvlan.tci || eth_type_vlan(swkey->eth.type)) {
- if (ovs_nla_put_vlan(skb, &output->eth.cvlan, is_mask))
+ eth_key = nla_data(nla);
+ ether_addr_copy(eth_key->eth_src, output->eth.src);
+ ether_addr_copy(eth_key->eth_dst, output->eth.dst);
+
+ if (swkey->eth.vlan.tci || eth_type_vlan(swkey->eth.type)) {
+ if (ovs_nla_put_vlan(skb, &output->eth.vlan, is_mask))
goto nla_put_failure;
- in_encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
- if (!swkey->eth.cvlan.tci)
+ encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
+ if (!swkey->eth.vlan.tci)
goto unencap;
+
+ if (swkey->eth.cvlan.tci || eth_type_vlan(swkey->eth.type)) {
+ if (ovs_nla_put_vlan(skb, &output->eth.cvlan, is_mask))
+ goto nla_put_failure;
+ in_encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
+ if (!swkey->eth.cvlan.tci)
+ goto unencap;
+ }
}
- }
- if (swkey->eth.type == htons(ETH_P_802_2)) {
- /*
- * Ethertype 802.2 is represented in the netlink with omitted
- * OVS_KEY_ATTR_ETHERTYPE in the flow key attribute, and
- * 0xffff in the mask attribute. Ethertype can also
- * be wildcarded.
- */
- if (is_mask && output->eth.type)
- if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE,
- output->eth.type))
- goto nla_put_failure;
- goto unencap;
+ if (swkey->eth.type == htons(ETH_P_802_2)) {
+ /*
+ * Ethertype 802.2 is represented in the netlink with omitted
+ * OVS_KEY_ATTR_ETHERTYPE in the flow key attribute, and
+ * 0xffff in the mask attribute. Ethertype can also
+ * be wildcarded.
+ */
+ if (is_mask && output->eth.type)
+ if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE,
+ output->eth.type))
+ goto nla_put_failure;
+ goto unencap;
+ }
}
if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, output->eth.type))
@@ -2126,8 +2159,8 @@ static bool validate_masked(u8 *data, int len)
static int validate_set(const struct nlattr *a,
const struct sw_flow_key *flow_key,
- struct sw_flow_actions **sfa,
- bool *skip_copy, __be16 eth_type, bool masked, bool log)
+ struct sw_flow_actions **sfa, bool *skip_copy,
+ u8 mac_proto, __be16 eth_type, bool masked, bool log)
{
const struct nlattr *ovs_key = nla_data(a);
int key_type = nla_type(ovs_key);
@@ -2157,9 +2190,12 @@ static int validate_set(const struct nlattr *a,
case OVS_KEY_ATTR_SKB_MARK:
case OVS_KEY_ATTR_CT_MARK:
case OVS_KEY_ATTR_CT_LABELS:
- case OVS_KEY_ATTR_ETHERNET:
break;
+ case OVS_KEY_ATTR_ETHERNET:
+ if (mac_proto != MAC_PROTO_ETHERNET)
+ return -EINVAL;
+
case OVS_KEY_ATTR_TUNNEL:
if (masked)
return -EINVAL; /* Masked tunnel set not supported. */
@@ -2324,6 +2360,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
int depth, struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci, bool log)
{
+ u8 mac_proto = ovs_key_mac_proto(key);
const struct nlattr *a;
int rem, err;
@@ -2346,6 +2383,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
[OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash),
[OVS_ACTION_ATTR_CT] = (u32)-1,
[OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc),
+ [OVS_ACTION_ATTR_PUSH_ETH] = sizeof(struct ovs_action_push_eth),
+ [OVS_ACTION_ATTR_POP_ETH] = 0,
};
const struct ovs_action_push_vlan *vlan;
int type = nla_type(a);
@@ -2394,10 +2433,14 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
}
case OVS_ACTION_ATTR_POP_VLAN:
+ if (mac_proto != MAC_PROTO_ETHERNET)
+ return -EINVAL;
vlan_tci = htons(0);
break;
case OVS_ACTION_ATTR_PUSH_VLAN:
+ if (mac_proto != MAC_PROTO_ETHERNET)
+ return -EINVAL;
vlan = nla_data(a);
if (!eth_type_vlan(vlan->vlan_tpid))
return -EINVAL;
@@ -2447,14 +2490,16 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
case OVS_ACTION_ATTR_SET:
err = validate_set(a, key, sfa,
- &skip_copy, eth_type, false, log);
+ &skip_copy, mac_proto, eth_type,
+ false, log);
if (err)
return err;
break;
case OVS_ACTION_ATTR_SET_MASKED:
err = validate_set(a, key, sfa,
- &skip_copy, eth_type, true, log);
+ &skip_copy, mac_proto, eth_type,
+ true, log);
if (err)
return err;
break;
@@ -2474,6 +2519,22 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
skip_copy = true;
break;
+ case OVS_ACTION_ATTR_PUSH_ETH:
+ /* Disallow pushing an Ethernet header if one
+ * is already present */
+ if (mac_proto != MAC_PROTO_NONE)
+ return -EINVAL;
+ mac_proto = MAC_PROTO_NONE;
+ break;
+
+ case OVS_ACTION_ATTR_POP_ETH:
+ if (mac_proto != MAC_PROTO_ETHERNET)
+ return -EINVAL;
+ if (vlan_tci & htons(VLAN_TAG_PRESENT))
+ return -EINVAL;
+ mac_proto = MAC_PROTO_ETHERNET;
+ break;
+
default:
OVS_NLERR(log, "Unknown Action type %d", type);
return -EINVAL;
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index e7da29021b38..d5d6caecd072 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -89,15 +89,6 @@ static const struct ethtool_ops internal_dev_ethtool_ops = {
.get_link = ethtool_op_get_link,
};
-static int internal_dev_change_mtu(struct net_device *netdev, int new_mtu)
-{
- if (new_mtu < 68)
- return -EINVAL;
-
- netdev->mtu = new_mtu;
- return 0;
-}
-
static void internal_dev_destructor(struct net_device *dev)
{
struct vport *vport = ovs_internal_dev_get_vport(dev);
@@ -148,7 +139,6 @@ static const struct net_device_ops internal_dev_netdev_ops = {
.ndo_stop = internal_dev_stop,
.ndo_start_xmit = internal_dev_xmit,
.ndo_set_mac_address = eth_mac_addr,
- .ndo_change_mtu = internal_dev_change_mtu,
.ndo_get_stats64 = internal_get_stats,
.ndo_set_rx_headroom = internal_set_rx_headroom,
};
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index 4e3972344aa6..0389398fa4ab 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -57,8 +57,10 @@ static void netdev_port_receive(struct sk_buff *skb)
if (unlikely(!skb))
return;
- skb_push(skb, ETH_HLEN);
- skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
+ if (skb->dev->type == ARPHRD_ETHER) {
+ skb_push(skb, ETH_HLEN);
+ skb_postpush_rcsum(skb, skb->data, ETH_HLEN);
+ }
ovs_vport_receive(vport, skb, skb_tunnel_info(skb));
return;
error:
@@ -97,7 +99,8 @@ struct vport *ovs_netdev_link(struct vport *vport, const char *name)
}
if (vport->dev->flags & IFF_LOOPBACK ||
- vport->dev->type != ARPHRD_ETHER ||
+ (vport->dev->type != ARPHRD_ETHER &&
+ vport->dev->type != ARPHRD_NONE) ||
ovs_is_internal_dev(vport->dev)) {
err = -EINVAL;
goto error_put;
@@ -162,7 +165,6 @@ void ovs_netdev_detach_dev(struct vport *vport)
netdev_master_upper_dev_get(vport->dev));
dev_set_promiscuity(vport->dev, -1);
}
-EXPORT_SYMBOL_GPL(ovs_netdev_detach_dev);
static void netdev_destroy(struct vport *vport)
{
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 7387418ac514..b6c8524032a0 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -463,27 +463,11 @@ int ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
ovs_dp_process_packet(skb, &key);
return 0;
}
-EXPORT_SYMBOL_GPL(ovs_vport_receive);
-static void free_vport_rcu(struct rcu_head *rcu)
+static unsigned int packet_length(const struct sk_buff *skb,
+ struct net_device *dev)
{
- struct vport *vport = container_of(rcu, struct vport, rcu);
-
- ovs_vport_free(vport);
-}
-
-void ovs_vport_deferred_free(struct vport *vport)
-{
- if (!vport)
- return;
-
- call_rcu(&vport->rcu, free_vport_rcu);
-}
-EXPORT_SYMBOL_GPL(ovs_vport_deferred_free);
-
-static unsigned int packet_length(const struct sk_buff *skb)
-{
- unsigned int length = skb->len - ETH_HLEN;
+ unsigned int length = skb->len - dev->hard_header_len;
if (!skb_vlan_tag_present(skb) &&
eth_type_vlan(skb->protocol))
@@ -497,14 +481,34 @@ static unsigned int packet_length(const struct sk_buff *skb)
return length;
}
-void ovs_vport_send(struct vport *vport, struct sk_buff *skb)
+void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto)
{
int mtu = vport->dev->mtu;
- if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) {
+ switch (vport->dev->type) {
+ case ARPHRD_NONE:
+ if (mac_proto == MAC_PROTO_ETHERNET) {
+ skb_reset_network_header(skb);
+ skb_reset_mac_len(skb);
+ skb->protocol = htons(ETH_P_TEB);
+ } else if (mac_proto != MAC_PROTO_NONE) {
+ WARN_ON_ONCE(1);
+ goto drop;
+ }
+ break;
+ case ARPHRD_ETHER:
+ if (mac_proto != MAC_PROTO_ETHERNET)
+ goto drop;
+ break;
+ default:
+ goto drop;
+ }
+
+ if (unlikely(packet_length(skb, vport->dev) > mtu &&
+ !skb_is_gso(skb))) {
net_warn_ratelimited("%s: dropped over-mtu packet: %d > %d\n",
vport->dev->name,
- packet_length(skb), mtu);
+ packet_length(skb, vport->dev), mtu);
vport->dev->stats.tx_errors++;
goto drop;
}
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index f01f28a567ad..cda66c26ad08 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -149,7 +149,6 @@ struct vport_ops {
struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *,
const struct vport_parms *);
void ovs_vport_free(struct vport *);
-void ovs_vport_deferred_free(struct vport *vport);
#define VPORT_ALIGN 8
@@ -198,6 +197,6 @@ int __ovs_vport_ops_register(struct vport_ops *ops);
})
void ovs_vport_ops_unregister(struct vport_ops *ops);
-void ovs_vport_send(struct vport *vport, struct sk_buff *skb);
+void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto);
#endif /* vport.h */
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-25 10:21:27 +0300