* %OVS_USERSPACE_ATTR_EGRESS_TUN_PORT attribute, which is sent only if the
* output port is actually a tunnel port. Contains the output tunnel key
* extracted from the packet as nested %OVS_TUNNEL_KEY_ATTR_* attributes.
+ * @OVS_PACKET_ATTR_MRU: Present for an %OVS_PACKET_CMD_ACTION and
+ * %OVS_PACKET_ATTR_USERSPACE action specify the Maximum received fragment
+ * size.
*
* These attributes follow the &struct ovs_header within the Generic Netlink
* payload for %OVS_PACKET_* commands.
OVS_PACKET_ATTR_UNUSED2,
OVS_PACKET_ATTR_PROBE, /* Packet operation is a feature probe,
error logging should be suppressed. */
+ OVS_PACKET_ATTR_MRU, /* Maximum received IP fragment size. */
__OVS_PACKET_ATTR_MAX
};
OVS_KEY_ATTR_MPLS, /* array of struct ovs_key_mpls.
* The implementation may restrict
* the accepted length of the array. */
+ OVS_KEY_ATTR_CT_STATE, /* u8 bitmask of OVS_CS_F_* */
+ OVS_KEY_ATTR_CT_ZONE, /* u16 connection tracking zone. */
#ifdef __KERNEL__
OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */
__u8 nd_tll[ETH_ALEN];
};
+/* OVS_KEY_ATTR_CT_STATE flags */
+#define OVS_CS_F_NEW 0x01 /* Beginning of a new connection. */
+#define OVS_CS_F_ESTABLISHED 0x02 /* Part of an existing connection. */
+#define OVS_CS_F_RELATED 0x04 /* Related to an established
+ * connection. */
+#define OVS_CS_F_INVALID 0x20 /* Could not track connection. */
+#define OVS_CS_F_REPLY_DIR 0x40 /* Flow is in the reply direction. */
+#define OVS_CS_F_TRACKED 0x80 /* Conntrack has occurred. */
+
/**
* enum ovs_flow_attr - attributes for %OVS_FLOW_* commands.
* @OVS_FLOW_ATTR_KEY: Nested %OVS_KEY_ATTR_* attributes specifying the flow
uint32_t hash_basis;
};
+/**
+ * enum ovs_ct_attr - Attributes for %OVS_ACTION_ATTR_CT action.
+ * @OVS_CT_ATTR_FLAGS: u32 connection tracking flags.
+ * @OVS_CT_ATTR_ZONE: u16 connection tracking zone.
+ */
+enum ovs_ct_attr {
+ OVS_CT_ATTR_UNSPEC,
+ OVS_CT_ATTR_FLAGS, /* u8 bitmask of OVS_CT_F_*. */
+ OVS_CT_ATTR_ZONE, /* u16 zone id. */
+ __OVS_CT_ATTR_MAX
+};
+
+#define OVS_CT_ATTR_MAX (__OVS_CT_ATTR_MAX - 1)
+
+/*
+ * OVS_CT_ATTR_FLAGS flags - bitmask of %OVS_CT_F_*
+ * @OVS_CT_F_COMMIT: Commits the flow to the conntrack table. This allows
+ * future packets for the same connection to be identified as 'established'
+ * or 'related'.
+ */
+#define OVS_CT_F_COMMIT 0x01
+
/**
* enum ovs_action_attr - Action types.
*
* indicate the new packet contents. This could potentially still be
* %ETH_P_MPLS if the resulting MPLS label stack is not empty. If there
* is no MPLS label stack, as determined by ethertype, no action is taken.
+ * @OVS_ACTION_ATTR_CT: Track the connection. Populate the conntrack-related
+ * entries in the flow key.
*
* Only a single header can be set with a single %OVS_ACTION_ATTR_SET. Not all
* fields within a header are modifiable, e.g. the IPv4 protocol and fragment
* data immediately followed by a mask.
* The data must be zero for the unmasked
* bits. */
+ OVS_ACTION_ATTR_CT, /* One nested OVS_CT_ATTR_* . */
__OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted
* from userspace. */
If unsure, say N.
+config OPENVSWITCH_CONNTRACK
+ bool "Open vSwitch conntrack action support"
+ depends on OPENVSWITCH
+ depends on NF_CONNTRACK
+ default OPENVSWITCH
+ ---help---
+ If you say Y here, then Open vSwitch module will be able to pass
+ packets through conntrack.
+
+ Say N to exclude this support and reduce the binary size.
+
config OPENVSWITCH_GRE
tristate "Open vSwitch GRE tunneling support"
depends on OPENVSWITCH
vport-internal_dev.o \
vport-netdev.o
+openvswitch-$(CONFIG_OPENVSWITCH_CONNTRACK) += conntrack.o
+
obj-$(CONFIG_OPENVSWITCH_VXLAN)+= vport-vxlan.o
obj-$(CONFIG_OPENVSWITCH_GENEVE)+= vport-geneve.o
obj-$(CONFIG_OPENVSWITCH_GRE) += vport-gre.o
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/openvswitch.h>
+#include <linux/netfilter_ipv6.h>
#include <linux/sctp.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/if_arp.h>
#include <linux/if_vlan.h>
+#include <net/dst.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/checksum.h>
#include "datapath.h"
#include "flow.h"
+#include "conntrack.h"
#include "vport.h"
static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key pkt_key;
};
+#define MAX_L2_LEN (VLAN_ETH_HLEN + 3 * MPLS_HLEN)
+struct ovs_frag_data {
+ unsigned long dst;
+ struct vport *vport;
+ struct ovs_skb_cb cb;
+ __be16 inner_protocol;
+ __u16 vlan_tci;
+ __be16 vlan_proto;
+ unsigned int l2_len;
+ u8 l2_data[MAX_L2_LEN];
+};
+
+static DEFINE_PER_CPU(struct ovs_frag_data, ovs_frag_data_storage);
+
#define DEFERRED_ACTION_FIFO_SIZE 10
struct action_fifo {
int head;
return 0;
}
-static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port)
+static int ovs_vport_output(struct sock *sock, struct sk_buff *skb)
+{
+ struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage);
+ struct vport *vport = data->vport;
+
+ if (skb_cow_head(skb, data->l2_len) < 0) {
+ kfree_skb(skb);
+ return -ENOMEM;
+ }
+
+ __skb_dst_copy(skb, data->dst);
+ *OVS_CB(skb) = data->cb;
+ skb->inner_protocol = data->inner_protocol;
+ skb->vlan_tci = data->vlan_tci;
+ skb->vlan_proto = data->vlan_proto;
+
+ /* Reconstruct the MAC header. */
+ skb_push(skb, data->l2_len);
+ memcpy(skb->data, &data->l2_data, data->l2_len);
+ ovs_skb_postpush_rcsum(skb, skb->data, data->l2_len);
+ skb_reset_mac_header(skb);
+
+ ovs_vport_send(vport, skb);
+ return 0;
+}
+
+static unsigned int
+ovs_dst_get_mtu(const struct dst_entry *dst)
+{
+ return dst->dev->mtu;
+}
+
+static struct dst_ops ovs_dst_ops = {
+ .family = AF_UNSPEC,
+ .mtu = ovs_dst_get_mtu,
+};
+
+/* 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)
+{
+ unsigned int hlen = skb_network_offset(skb);
+ struct ovs_frag_data *data;
+
+ data = this_cpu_ptr(&ovs_frag_data_storage);
+ data->dst = skb->_skb_refdst;
+ data->vport = vport;
+ data->cb = *OVS_CB(skb);
+ data->inner_protocol = skb->inner_protocol;
+ data->vlan_tci = skb->vlan_tci;
+ data->vlan_proto = skb->vlan_proto;
+ data->l2_len = hlen;
+ memcpy(&data->l2_data, skb->data, hlen);
+
+ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
+ skb_pull(skb, hlen);
+}
+
+static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru,
+ __be16 ethertype)
+{
+ if (skb_network_offset(skb) > MAX_L2_LEN) {
+ OVS_NLERR(1, "L2 header too long to fragment");
+ return;
+ }
+
+ if (ethertype == htons(ETH_P_IP)) {
+ struct dst_entry ovs_dst;
+ unsigned long orig_dst;
+
+ prepare_frag(vport, skb);
+ dst_init(&ovs_dst, &ovs_dst_ops, NULL, 1,
+ DST_OBSOLETE_NONE, DST_NOCOUNT);
+ ovs_dst.dev = vport->dev;
+
+ orig_dst = skb->_skb_refdst;
+ skb_dst_set_noref(skb, &ovs_dst);
+ IPCB(skb)->frag_max_size = mru;
+
+ ip_do_fragment(skb->sk, skb, ovs_vport_output);
+ refdst_drop(orig_dst);
+ } else if (ethertype == htons(ETH_P_IPV6)) {
+ const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
+ unsigned long orig_dst;
+ struct rt6_info ovs_rt;
+
+ if (!v6ops) {
+ kfree_skb(skb);
+ return;
+ }
+
+ prepare_frag(vport, skb);
+ memset(&ovs_rt, 0, sizeof(ovs_rt));
+ dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL, 1,
+ DST_OBSOLETE_NONE, DST_NOCOUNT);
+ ovs_rt.dst.dev = vport->dev;
+
+ orig_dst = skb->_skb_refdst;
+ skb_dst_set_noref(skb, &ovs_rt.dst);
+ IP6CB(skb)->frag_max_size = mru;
+
+ v6ops->fragment(skb->sk, skb, ovs_vport_output);
+ refdst_drop(orig_dst);
+ } else {
+ WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
+ ovs_vport_name(vport), ntohs(ethertype), mru,
+ vport->dev->mtu);
+ kfree_skb(skb);
+ }
+}
+
+static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
+ struct sw_flow_key *key)
{
struct vport *vport = ovs_vport_rcu(dp, out_port);
- if (likely(vport))
- ovs_vport_send(vport, skb);
- else
+ if (likely(vport)) {
+ u16 mru = OVS_CB(skb)->mru;
+
+ if (likely(!mru || (skb->len <= mru + ETH_HLEN))) {
+ ovs_vport_send(vport, skb);
+ } else if (mru <= vport->dev->mtu) {
+ __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(vport, skb, mru, ethertype);
+ } else {
+ kfree_skb(skb);
+ }
+ } else {
kfree_skb(skb);
+ }
}
static int output_userspace(struct datapath *dp, struct sk_buff *skb,
memset(&upcall, 0, sizeof(upcall));
upcall.cmd = OVS_PACKET_CMD_ACTION;
+ upcall.mru = OVS_CB(skb)->mru;
for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
a = nla_next(a, &rem)) {
err = set_mpls(skb, flow_key, nla_data(a), get_mask(a,
__be32 *));
break;
+
+ case OVS_KEY_ATTR_CT_STATE:
+ case OVS_KEY_ATTR_CT_ZONE:
+ err = -EINVAL;
+ break;
}
return err;
struct sk_buff *out_skb = skb_clone(skb, GFP_ATOMIC);
if (out_skb)
- do_output(dp, out_skb, prev_port);
+ do_output(dp, out_skb, prev_port, key);
prev_port = -1;
}
case OVS_ACTION_ATTR_SAMPLE:
err = sample(dp, skb, key, a, attr, len);
break;
+
+ case OVS_ACTION_ATTR_CT:
+ err = ovs_ct_execute(ovs_dp_get_net(dp), skb, key,
+ nla_data(a));
+
+ /* Hide stolen IP fragments from user space. */
+ if (err == -EINPROGRESS)
+ return 0;
+ break;
}
if (unlikely(err)) {
}
if (prev_port != -1)
- do_output(dp, skb, prev_port);
+ do_output(dp, skb, prev_port, key);
else
consume_skb(skb);
--- /dev/null
+/*
+ * Copyright (c) 2015 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/openvswitch.h>
+#include <net/ip.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+
+#include "datapath.h"
+#include "conntrack.h"
+#include "flow.h"
+#include "flow_netlink.h"
+
+struct ovs_ct_len_tbl {
+ size_t maxlen;
+ size_t minlen;
+};
+
+/* Conntrack action context for execution. */
+struct ovs_conntrack_info {
+ struct nf_conntrack_zone zone;
+ struct nf_conn *ct;
+ u32 flags;
+ u16 family;
+};
+
+static u16 key_to_nfproto(const struct sw_flow_key *key)
+{
+ switch (ntohs(key->eth.type)) {
+ case ETH_P_IP:
+ return NFPROTO_IPV4;
+ case ETH_P_IPV6:
+ return NFPROTO_IPV6;
+ default:
+ return NFPROTO_UNSPEC;
+ }
+}
+
+/* Map SKB connection state into the values used by flow definition. */
+static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo)
+{
+ u8 ct_state = OVS_CS_F_TRACKED;
+
+ switch (ctinfo) {
+ case IP_CT_ESTABLISHED_REPLY:
+ case IP_CT_RELATED_REPLY:
+ case IP_CT_NEW_REPLY:
+ ct_state |= OVS_CS_F_REPLY_DIR;
+ break;
+ default:
+ break;
+ }
+
+ switch (ctinfo) {
+ case IP_CT_ESTABLISHED:
+ case IP_CT_ESTABLISHED_REPLY:
+ ct_state |= OVS_CS_F_ESTABLISHED;
+ break;
+ case IP_CT_RELATED:
+ case IP_CT_RELATED_REPLY:
+ ct_state |= OVS_CS_F_RELATED;
+ break;
+ case IP_CT_NEW:
+ case IP_CT_NEW_REPLY:
+ ct_state |= OVS_CS_F_NEW;
+ break;
+ default:
+ break;
+ }
+
+ return ct_state;
+}
+
+static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state,
+ const struct nf_conntrack_zone *zone)
+{
+ key->ct.state = state;
+ key->ct.zone = zone->id;
+}
+
+/* Update 'key' based on skb->nfct. If 'post_ct' is true, then OVS has
+ * previously sent the packet to conntrack via the ct action.
+ */
+static void ovs_ct_update_key(const struct sk_buff *skb,
+ struct sw_flow_key *key, bool post_ct)
+{
+ const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt;
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
+ u8 state = 0;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct) {
+ state = ovs_ct_get_state(ctinfo);
+ if (ct->master)
+ state |= OVS_CS_F_RELATED;
+ zone = nf_ct_zone(ct);
+ } else if (post_ct) {
+ state = OVS_CS_F_TRACKED | OVS_CS_F_INVALID;
+ }
+ __ovs_ct_update_key(key, state, zone);
+}
+
+void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key)
+{
+ ovs_ct_update_key(skb, key, false);
+}
+
+int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb)
+{
+ if (nla_put_u8(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state))
+ return -EMSGSIZE;
+
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
+ nla_put_u16(skb, OVS_KEY_ATTR_CT_ZONE, key->ct.zone))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int handle_fragments(struct net *net, struct sw_flow_key *key,
+ u16 zone, struct sk_buff *skb)
+{
+ struct ovs_skb_cb ovs_cb = *OVS_CB(skb);
+
+ if (key->eth.type == htons(ETH_P_IP)) {
+ enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;
+ int err;
+
+ memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
+ err = ip_defrag(skb, user);
+ if (err)
+ return err;
+
+ ovs_cb.mru = IPCB(skb)->frag_max_size;
+ } else if (key->eth.type == htons(ETH_P_IPV6)) {
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
+ enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
+ struct sk_buff *reasm;
+
+ memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
+ reasm = nf_ct_frag6_gather(skb, user);
+ if (!reasm)
+ return -EINPROGRESS;
+
+ if (skb == reasm)
+ return -EINVAL;
+
+ key->ip.proto = ipv6_hdr(reasm)->nexthdr;
+ skb_morph(skb, reasm);
+ consume_skb(reasm);
+ ovs_cb.mru = IP6CB(skb)->frag_max_size;
+#else
+ return -EPFNOSUPPORT;
+#endif
+ } else {
+ return -EPFNOSUPPORT;
+ }
+
+ key->ip.frag = OVS_FRAG_TYPE_NONE;
+ skb_clear_hash(skb);
+ skb->ignore_df = 1;
+ *OVS_CB(skb) = ovs_cb;
+
+ return 0;
+}
+
+static struct nf_conntrack_expect *
+ovs_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone,
+ u16 proto, const struct sk_buff *skb)
+{
+ struct nf_conntrack_tuple tuple;
+
+ if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, &tuple))
+ return NULL;
+ return __nf_ct_expect_find(net, zone, &tuple);
+}
+
+/* Determine whether skb->nfct is equal to the result of conntrack lookup. */
+static bool skb_nfct_cached(const struct net *net, const struct sk_buff *skb,
+ const struct ovs_conntrack_info *info)
+{
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (!ct)
+ return false;
+ if (!net_eq(net, read_pnet(&ct->ct_net)))
+ return false;
+ if (!nf_ct_zone_equal_any(info->ct, nf_ct_zone(ct)))
+ return false;
+
+ return true;
+}
+
+static int __ovs_ct_lookup(struct net *net, const struct sw_flow_key *key,
+ const struct ovs_conntrack_info *info,
+ struct sk_buff *skb)
+{
+ /* If we are recirculating packets to match on conntrack fields and
+ * committing with a separate conntrack action, then we don't need to
+ * actually run the packet through conntrack twice unless it's for a
+ * different zone.
+ */
+ if (!skb_nfct_cached(net, skb, info)) {
+ struct nf_conn *tmpl = info->ct;
+
+ /* Associate skb with specified zone. */
+ if (tmpl) {
+ if (skb->nfct)
+ nf_conntrack_put(skb->nfct);
+ nf_conntrack_get(&tmpl->ct_general);
+ skb->nfct = &tmpl->ct_general;
+ skb->nfctinfo = IP_CT_NEW;
+ }
+
+ if (nf_conntrack_in(net, info->family, NF_INET_PRE_ROUTING,
+ skb) != NF_ACCEPT)
+ return -ENOENT;
+ }
+
+ return 0;
+}
+
+/* Lookup connection and read fields into key. */
+static int ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
+ const struct ovs_conntrack_info *info,
+ struct sk_buff *skb)
+{
+ struct nf_conntrack_expect *exp;
+
+ exp = ovs_ct_expect_find(net, &info->zone, info->family, skb);
+ if (exp) {
+ u8 state;
+
+ state = OVS_CS_F_TRACKED | OVS_CS_F_NEW | OVS_CS_F_RELATED;
+ __ovs_ct_update_key(key, state, &info->zone);
+ } else {
+ int err;
+
+ err = __ovs_ct_lookup(net, key, info, skb);
+ if (err)
+ return err;
+
+ ovs_ct_update_key(skb, key, true);
+ }
+
+ return 0;
+}
+
+/* Lookup connection and confirm if unconfirmed. */
+static int ovs_ct_commit(struct net *net, struct sw_flow_key *key,
+ const struct ovs_conntrack_info *info,
+ struct sk_buff *skb)
+{
+ u8 state;
+ int err;
+
+ state = key->ct.state;
+ if (key->ct.zone == info->zone.id &&
+ ((state & OVS_CS_F_TRACKED) && !(state & OVS_CS_F_NEW))) {
+ /* Previous lookup has shown that this connection is already
+ * tracked and committed. Skip committing.
+ */
+ return 0;
+ }
+
+ err = __ovs_ct_lookup(net, key, info, skb);
+ if (err)
+ return err;
+ if (nf_conntrack_confirm(skb) != NF_ACCEPT)
+ return -EINVAL;
+
+ ovs_ct_update_key(skb, key, true);
+
+ return 0;
+}
+
+int ovs_ct_execute(struct net *net, struct sk_buff *skb,
+ struct sw_flow_key *key,
+ const struct ovs_conntrack_info *info)
+{
+ int nh_ofs;
+ int err;
+
+ /* The conntrack module expects to be working at L3. */
+ nh_ofs = skb_network_offset(skb);
+ skb_pull(skb, nh_ofs);
+
+ if (key->ip.frag != OVS_FRAG_TYPE_NONE) {
+ err = handle_fragments(net, key, info->zone.id, skb);
+ if (err)
+ return err;
+ }
+
+ if (info->flags & OVS_CT_F_COMMIT)
+ err = ovs_ct_commit(net, key, info, skb);
+ else
+ err = ovs_ct_lookup(net, key, info, skb);
+
+ skb_push(skb, nh_ofs);
+ return err;
+}
+
+static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = {
+ [OVS_CT_ATTR_FLAGS] = { .minlen = sizeof(u32),
+ .maxlen = sizeof(u32) },
+ [OVS_CT_ATTR_ZONE] = { .minlen = sizeof(u16),
+ .maxlen = sizeof(u16) },
+};
+
+static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info,
+ bool log)
+{
+ struct nlattr *a;
+ int rem;
+
+ nla_for_each_nested(a, attr, rem) {
+ int type = nla_type(a);
+ int maxlen = ovs_ct_attr_lens[type].maxlen;
+ int minlen = ovs_ct_attr_lens[type].minlen;
+
+ if (type > OVS_CT_ATTR_MAX) {
+ OVS_NLERR(log,
+ "Unknown conntrack attr (type=%d, max=%d)",
+ type, OVS_CT_ATTR_MAX);
+ return -EINVAL;
+ }
+ if (nla_len(a) < minlen || nla_len(a) > maxlen) {
+ OVS_NLERR(log,
+ "Conntrack attr type has unexpected length (type=%d, length=%d, expected=%d)",
+ type, nla_len(a), maxlen);
+ return -EINVAL;
+ }
+
+ switch (type) {
+ case OVS_CT_ATTR_FLAGS:
+ info->flags = nla_get_u32(a);
+ break;
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+ case OVS_CT_ATTR_ZONE:
+ info->zone.id = nla_get_u16(a);
+ break;
+#endif
+ default:
+ OVS_NLERR(log, "Unknown conntrack attr (%d)",
+ type);
+ return -EINVAL;
+ }
+ }
+
+ if (rem > 0) {
+ OVS_NLERR(log, "Conntrack attr has %d unknown bytes", rem);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+bool ovs_ct_verify(enum ovs_key_attr attr)
+{
+ if (attr == OVS_KEY_ATTR_CT_STATE)
+ return true;
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
+ attr == OVS_KEY_ATTR_CT_ZONE)
+ return true;
+
+ return false;
+}
+
+int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
+ const struct sw_flow_key *key,
+ struct sw_flow_actions **sfa, bool log)
+{
+ struct ovs_conntrack_info ct_info;
+ u16 family;
+ int err;
+
+ family = key_to_nfproto(key);
+ if (family == NFPROTO_UNSPEC) {
+ OVS_NLERR(log, "ct family unspecified");
+ return -EINVAL;
+ }
+
+ memset(&ct_info, 0, sizeof(ct_info));
+ ct_info.family = family;
+
+ nf_ct_zone_init(&ct_info.zone, NF_CT_DEFAULT_ZONE_ID,
+ NF_CT_DEFAULT_ZONE_DIR, 0);
+
+ err = parse_ct(attr, &ct_info, log);
+ if (err)
+ return err;
+
+ /* Set up template for tracking connections in specific zones. */
+ ct_info.ct = nf_ct_tmpl_alloc(net, &ct_info.zone, GFP_KERNEL);
+ if (!ct_info.ct) {
+ OVS_NLERR(log, "Failed to allocate conntrack template");
+ return -ENOMEM;
+ }
+
+ err = ovs_nla_add_action(sfa, OVS_ACTION_ATTR_CT, &ct_info,
+ sizeof(ct_info), log);
+ if (err)
+ goto err_free_ct;
+
+ __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status);
+ nf_conntrack_get(&ct_info.ct->ct_general);
+ return 0;
+err_free_ct:
+ nf_conntrack_free(ct_info.ct);
+ return err;
+}
+
+int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info,
+ struct sk_buff *skb)
+{
+ struct nlattr *start;
+
+ start = nla_nest_start(skb, OVS_ACTION_ATTR_CT);
+ if (!start)
+ return -EMSGSIZE;
+
+ if (nla_put_u32(skb, OVS_CT_ATTR_FLAGS, ct_info->flags))
+ return -EMSGSIZE;
+ if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
+ nla_put_u16(skb, OVS_CT_ATTR_ZONE, ct_info->zone.id))
+ return -EMSGSIZE;
+
+ nla_nest_end(skb, start);
+
+ return 0;
+}
+
+void ovs_ct_free_action(const struct nlattr *a)
+{
+ struct ovs_conntrack_info *ct_info = nla_data(a);
+
+ if (ct_info->ct)
+ nf_ct_put(ct_info->ct);
+}
--- /dev/null
+/*
+ * Copyright (c) 2015 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef OVS_CONNTRACK_H
+#define OVS_CONNTRACK_H 1
+
+#include "flow.h"
+
+struct ovs_conntrack_info;
+enum ovs_key_attr;
+
+#if defined(CONFIG_OPENVSWITCH_CONNTRACK)
+bool ovs_ct_verify(enum ovs_key_attr attr);
+int ovs_ct_copy_action(struct net *, const struct nlattr *,
+ const struct sw_flow_key *, struct sw_flow_actions **,
+ bool log);
+int ovs_ct_action_to_attr(const struct ovs_conntrack_info *, struct sk_buff *);
+
+int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *,
+ const struct ovs_conntrack_info *);
+
+void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key);
+int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb);
+void ovs_ct_free_action(const struct nlattr *a);
+#else
+#include <linux/errno.h>
+
+static inline bool ovs_ct_verify(int attr)
+{
+ return false;
+}
+
+static inline int ovs_ct_copy_action(struct net *net, const struct nlattr *nla,
+ const struct sw_flow_key *key,
+ struct sw_flow_actions **acts, bool log)
+{
+ return -ENOTSUPP;
+}
+
+static inline int ovs_ct_action_to_attr(const struct ovs_conntrack_info *info,
+ struct sk_buff *skb)
+{
+ return -ENOTSUPP;
+}
+
+static inline int ovs_ct_execute(struct net *net, struct sk_buff *skb,
+ struct sw_flow_key *key,
+ const struct ovs_conntrack_info *info)
+{
+ return -ENOTSUPP;
+}
+
+static inline void ovs_ct_fill_key(const struct sk_buff *skb,
+ struct sw_flow_key *key)
+{
+ key->ct.state = 0;
+ key->ct.zone = 0;
+}
+
+static inline int ovs_ct_put_key(const struct sw_flow_key *key,
+ struct sk_buff *skb)
+{
+ return 0;
+}
+
+static inline void ovs_ct_free_action(const struct nlattr *a) { }
+#endif
+#endif /* ovs_conntrack.h */
memset(&upcall, 0, sizeof(upcall));
upcall.cmd = OVS_PACKET_CMD_MISS;
upcall.portid = ovs_vport_find_upcall_portid(p, skb);
+ upcall.mru = OVS_CB(skb)->mru;
error = ovs_dp_upcall(dp, skb, key, &upcall);
if (unlikely(error))
kfree_skb(skb);
if (upcall_info->actions_len)
size += nla_total_size(upcall_info->actions_len);
+ /* OVS_PACKET_ATTR_MRU */
+ if (upcall_info->mru)
+ size += nla_total_size(sizeof(upcall_info->mru));
+
return size;
}
+static void pad_packet(struct datapath *dp, struct sk_buff *skb)
+{
+ if (!(dp->user_features & OVS_DP_F_UNALIGNED)) {
+ size_t plen = NLA_ALIGN(skb->len) - skb->len;
+
+ if (plen > 0)
+ memset(skb_put(skb, plen), 0, plen);
+ }
+}
+
static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
const struct sw_flow_key *key,
const struct dp_upcall_info *upcall_info)
nla_nest_cancel(user_skb, nla);
}
+ /* Add OVS_PACKET_ATTR_MRU */
+ if (upcall_info->mru) {
+ if (nla_put_u16(user_skb, OVS_PACKET_ATTR_MRU,
+ upcall_info->mru)) {
+ err = -ENOBUFS;
+ goto out;
+ }
+ pad_packet(dp, user_skb);
+ }
+
/* Only reserve room for attribute header, packet data is added
* in skb_zerocopy() */
if (!(nla = nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, 0))) {
goto out;
/* Pad OVS_PACKET_ATTR_PACKET if linear copy was performed */
- if (!(dp->user_features & OVS_DP_F_UNALIGNED)) {
- size_t plen = NLA_ALIGN(user_skb->len) - user_skb->len;
-
- if (plen > 0)
- memset(skb_put(user_skb, plen), 0, plen);
- }
+ pad_packet(dp, user_skb);
((struct nlmsghdr *) user_skb->data)->nlmsg_len = user_skb->len;
static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
{
struct ovs_header *ovs_header = info->userhdr;
+ struct net *net = sock_net(skb->sk);
struct nlattr **a = info->attrs;
struct sw_flow_actions *acts;
struct sk_buff *packet;
struct datapath *dp;
struct ethhdr *eth;
struct vport *input_vport;
+ u16 mru = 0;
int len;
int err;
bool log = !a[OVS_PACKET_ATTR_PROBE];
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]);
+ packet->ignore_df = 1;
+ }
+ OVS_CB(packet)->mru = mru;
+
/* Build an sw_flow for sending this packet. */
flow = ovs_flow_alloc();
err = PTR_ERR(flow);
if (err)
goto err_flow_free;
- err = ovs_nla_copy_actions(a[OVS_PACKET_ATTR_ACTIONS],
+ err = ovs_nla_copy_actions(net, a[OVS_PACKET_ATTR_ACTIONS],
&flow->key, &acts, log);
if (err)
goto err_flow_free;
packet->mark = flow->key.phy.skb_mark;
rcu_read_lock();
- dp = get_dp_rcu(sock_net(skb->sk), ovs_header->dp_ifindex);
+ dp = get_dp_rcu(net, ovs_header->dp_ifindex);
err = -ENODEV;
if (!dp)
goto err_unlock;
if (!input_vport)
goto err_unlock;
+ packet->dev = input_vport->dev;
OVS_CB(packet)->input_vport = input_vport;
sf_acts = rcu_dereference(flow->sf_acts);
[OVS_PACKET_ATTR_KEY] = { .type = NLA_NESTED },
[OVS_PACKET_ATTR_ACTIONS] = { .type = NLA_NESTED },
[OVS_PACKET_ATTR_PROBE] = { .type = NLA_FLAG },
+ [OVS_PACKET_ATTR_MRU] = { .type = NLA_U16 },
};
static const struct genl_ops dp_packet_genl_ops[] = {
static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
{
+ struct net *net = sock_net(skb->sk);
struct nlattr **a = info->attrs;
struct ovs_header *ovs_header = info->userhdr;
struct sw_flow *flow = NULL, *new_flow;
goto err_kfree_flow;
/* Validate actions. */
- error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key,
- &acts, log);
+ error = ovs_nla_copy_actions(net, a[OVS_FLOW_ATTR_ACTIONS],
+ &new_flow->key, &acts, log);
if (error) {
OVS_NLERR(log, "Flow actions may not be safe on all matching packets.");
goto err_kfree_flow;
}
ovs_lock();
- dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+ dp = get_dp(net, ovs_header->dp_ifindex);
if (unlikely(!dp)) {
error = -ENODEV;
goto err_unlock_ovs;
}
/* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */
-static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
+static struct sw_flow_actions *get_flow_actions(struct net *net,
+ const struct nlattr *a,
const struct sw_flow_key *key,
const struct sw_flow_mask *mask,
bool log)
int error;
ovs_flow_mask_key(&masked_key, key, mask);
- error = ovs_nla_copy_actions(a, &masked_key, &acts, log);
+ error = ovs_nla_copy_actions(net, a, &masked_key, &acts, log);
if (error) {
OVS_NLERR(log,
"Actions may not be safe on all matching packets");
static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
{
+ struct net *net = sock_net(skb->sk);
struct nlattr **a = info->attrs;
struct ovs_header *ovs_header = info->userhdr;
struct sw_flow_key key;
/* Validate actions. */
if (a[OVS_FLOW_ATTR_ACTIONS]) {
- acts = get_flow_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, &mask,
- log);
+ acts = get_flow_actions(net, a[OVS_FLOW_ATTR_ACTIONS], &key,
+ &mask, log);
if (IS_ERR(acts)) {
error = PTR_ERR(acts);
goto error;
}
ovs_lock();
- dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+ dp = get_dp(net, ovs_header->dp_ifindex);
if (unlikely(!dp)) {
error = -ENODEV;
goto err_unlock_ovs;
#include <linux/u64_stats_sync.h>
#include <net/ip_tunnels.h>
+#include "conntrack.h"
#include "flow.h"
#include "flow_table.h"
#include "vport.h"
* NULL if the packet is not being tunneled.
* @input_vport: The original vport packet came in on. This value is cached
* when a packet is received by OVS.
+ * @mru: The maximum received fragement size; 0 if the packet is not
+ * fragmented.
*/
struct ovs_skb_cb {
struct ip_tunnel_info *egress_tun_info;
struct vport *input_vport;
+ u16 mru;
};
#define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
* then no packet is sent and the packet is accounted in the datapath's @n_lost
* counter.
* @egress_tun_info: If nonnull, becomes %OVS_PACKET_ATTR_EGRESS_TUN_KEY.
+ * @mru: If not zero, Maximum received IP fragment size.
*/
struct dp_upcall_info {
const struct ip_tunnel_info *egress_tun_info;
int actions_len;
u32 portid;
u8 cmd;
+ u16 mru;
};
/**
#include "datapath.h"
#include "flow.h"
#include "flow_netlink.h"
+#include "conntrack.h"
u64 ovs_flow_used_time(unsigned long flow_jiffies)
{
key->phy.priority = skb->priority;
key->phy.in_port = OVS_CB(skb)->input_vport->port_no;
key->phy.skb_mark = skb->mark;
+ ovs_ct_fill_key(skb, key);
key->ovs_flow_hash = 0;
key->recirc_id = 0;
} nd;
} ipv6;
};
+ struct {
+ /* Connection tracking fields. */
+ u16 zone;
+ u8 state;
+ } ct;
+
} __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */
struct sw_flow_key_range {
/* Whenever adding new OVS_KEY_ FIELDS, we should consider
* updating this function.
*/
- BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 22);
+ BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 24);
return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */
+ nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */
+ nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */
+ nla_total_size(4) /* OVS_KEY_ATTR_DP_HASH */
+ nla_total_size(4) /* OVS_KEY_ATTR_RECIRC_ID */
+ + nla_total_size(1) /* OVS_KEY_ATTR_CT_STATE */
+ + nla_total_size(2) /* OVS_KEY_ATTR_CT_ZONE */
+ nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */
+ nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */
+ nla_total_size(4) /* OVS_KEY_ATTR_VLAN */
[OVS_KEY_ATTR_TUNNEL] = { .len = OVS_ATTR_NESTED,
.next = ovs_tunnel_key_lens, },
[OVS_KEY_ATTR_MPLS] = { .len = sizeof(struct ovs_key_mpls) },
+ [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u8) },
+ [OVS_KEY_ATTR_CT_ZONE] = { .len = sizeof(u16) },
};
static bool is_all_zero(const u8 *fp, size_t size)
return -EINVAL;
*attrs &= ~(1 << OVS_KEY_ATTR_TUNNEL);
}
+
+ if (*attrs & (1 << OVS_KEY_ATTR_CT_STATE) &&
+ ovs_ct_verify(OVS_KEY_ATTR_CT_STATE)) {
+ u8 ct_state = nla_get_u8(a[OVS_KEY_ATTR_CT_STATE]);
+
+ SW_FLOW_KEY_PUT(match, ct.state, ct_state, is_mask);
+ *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_STATE);
+ }
+ if (*attrs & (1 << OVS_KEY_ATTR_CT_ZONE) &&
+ ovs_ct_verify(OVS_KEY_ATTR_CT_ZONE)) {
+ u16 ct_zone = nla_get_u16(a[OVS_KEY_ATTR_CT_ZONE]);
+
+ SW_FLOW_KEY_PUT(match, ct.zone, ct_zone, is_mask);
+ *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ZONE);
+ }
return 0;
}
memset(&match, 0, sizeof(match));
match.key = key;
+ memset(&key->ct, 0, sizeof(key->ct));
key->phy.in_port = DP_MAX_PORTS;
return metadata_from_nlattrs(&match, &attrs, a, false, log);
if (nla_put_u32(skb, OVS_KEY_ATTR_SKB_MARK, output->phy.skb_mark))
goto nla_put_failure;
+ 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;
case OVS_ACTION_ATTR_SET:
ovs_nla_free_set_action(a);
break;
+ case OVS_ACTION_ATTR_CT:
+ ovs_ct_free_action(a);
+ break;
}
}
return a;
}
-static int add_action(struct sw_flow_actions **sfa, int attrtype,
- void *data, int len, bool log)
+int ovs_nla_add_action(struct sw_flow_actions **sfa, int attrtype, void *data,
+ int len, bool log)
{
struct nlattr *a;
int used = (*sfa)->actions_len;
int err;
- err = add_action(sfa, attrtype, NULL, 0, log);
+ err = ovs_nla_add_action(sfa, attrtype, NULL, 0, log);
if (err)
return err;
a->nla_len = sfa->actions_len - st_offset;
}
-static int __ovs_nla_copy_actions(const struct nlattr *attr,
+static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
const struct sw_flow_key *key,
int depth, struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci, bool log);
-static int validate_and_copy_sample(const struct nlattr *attr,
+static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
const struct sw_flow_key *key, int depth,
struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci, bool log)
start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE, log);
if (start < 0)
return start;
- err = add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY,
- nla_data(probability), sizeof(u32), log);
+ err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY,
+ nla_data(probability), sizeof(u32), log);
if (err)
return err;
st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS, log);
if (st_acts < 0)
return st_acts;
- err = __ovs_nla_copy_actions(actions, key, depth + 1, sfa,
+ err = __ovs_nla_copy_actions(net, actions, key, depth + 1, sfa,
eth_type, vlan_tci, log);
if (err)
return err;
return 0;
}
-static int __ovs_nla_copy_actions(const struct nlattr *attr,
+static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
const struct sw_flow_key *key,
int depth, struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci, bool log)
[OVS_ACTION_ATTR_SET] = (u32)-1,
[OVS_ACTION_ATTR_SET_MASKED] = (u32)-1,
[OVS_ACTION_ATTR_SAMPLE] = (u32)-1,
- [OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash)
+ [OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash),
+ [OVS_ACTION_ATTR_CT] = (u32)-1,
};
const struct ovs_action_push_vlan *vlan;
int type = nla_type(a);
break;
case OVS_ACTION_ATTR_SAMPLE:
- err = validate_and_copy_sample(a, key, depth, sfa,
+ err = validate_and_copy_sample(net, a, key, depth, sfa,
eth_type, vlan_tci, log);
if (err)
return err;
skip_copy = true;
break;
+ case OVS_ACTION_ATTR_CT:
+ err = ovs_ct_copy_action(net, a, key, sfa, log);
+ if (err)
+ return err;
+ skip_copy = true;
+ break;
+
default:
OVS_NLERR(log, "Unknown Action type %d", type);
return -EINVAL;
}
/* 'key' must be the masked key. */
-int ovs_nla_copy_actions(const struct nlattr *attr,
+int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
const struct sw_flow_key *key,
struct sw_flow_actions **sfa, bool log)
{
return PTR_ERR(*sfa);
(*sfa)->orig_len = nla_len(attr);
- err = __ovs_nla_copy_actions(attr, key, 0, sfa, key->eth.type,
+ err = __ovs_nla_copy_actions(net, attr, key, 0, sfa, key->eth.type,
key->eth.tci, log);
if (err)
ovs_nla_free_flow_actions(*sfa);
if (err)
return err;
break;
+
+ case OVS_ACTION_ATTR_CT:
+ err = ovs_ct_action_to_attr(nla_data(a), skb);
+ if (err)
+ return err;
+ break;
+
default:
if (nla_put(skb, type, nla_len(a), nla_data(a)))
return -EMSGSIZE;
const struct sw_flow_key *key, bool log);
u32 ovs_nla_get_ufid_flags(const struct nlattr *attr);
-int ovs_nla_copy_actions(const struct nlattr *attr,
+int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
const struct sw_flow_key *key,
struct sw_flow_actions **sfa, bool log);
+int ovs_nla_add_action(struct sw_flow_actions **sfa, int attrtype,
+ void *data, int len, bool log);
int ovs_nla_put_actions(const struct nlattr *attr,
int len, struct sk_buff *skb);
OVS_CB(skb)->input_vport = vport;
OVS_CB(skb)->egress_tun_info = NULL;
+ OVS_CB(skb)->mru = 0;
/* Extract flow from 'skb' into 'key'. */
error = ovs_flow_key_extract(tun_info, skb, &key);
if (unlikely(error)) {
projects / karo-tx-linux.git / commitdiff