From ceaa001a170e43608854d5290a48064f57b565ed Mon Sep 17 00:00:00 2001 From: William Tu Date: Wed, 4 Oct 2017 17:03:12 -0700 Subject: openvswitch: Add erspan tunnel support. Add erspan netlink interface for OVS. Signed-off-by: William Tu Cc: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux/openvswitch.h') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 156ee4cab82e..efdbfbfd3ee2 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -359,6 +359,7 @@ enum ovs_tunnel_key_attr { OVS_TUNNEL_KEY_ATTR_IPV6_SRC, /* struct in6_addr src IPv6 address. */ OVS_TUNNEL_KEY_ATTR_IPV6_DST, /* struct in6_addr dst IPv6 address. */ OVS_TUNNEL_KEY_ATTR_PAD, + OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, /* be32 ERSPAN index. */ __OVS_TUNNEL_KEY_ATTR_MAX }; -- cgit v1.2.3 From b8226962b1c49c784aeddb9d2fafbf53dfdc2190 Mon Sep 17 00:00:00 2001 From: Eric Garver Date: Tue, 10 Oct 2017 16:54:44 -0400 Subject: openvswitch: add ct_clear action This adds a ct_clear action for clearing conntrack state. ct_clear is currently implemented in OVS userspace, but is not backed by an action in the kernel datapath. This is useful for flows that may modify a packet tuple after a ct lookup has already occurred. Signed-off-by: Eric Garver Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 2 ++ net/openvswitch/actions.c | 4 ++++ net/openvswitch/conntrack.c | 11 +++++++++++ net/openvswitch/conntrack.h | 7 +++++++ net/openvswitch/flow_netlink.c | 5 +++++ 5 files changed, 29 insertions(+) (limited to 'include/uapi/linux/openvswitch.h') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index efdbfbfd3ee2..0cd6f8833147 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -807,6 +807,7 @@ struct ovs_action_push_eth { * packet. * @OVS_ACTION_ATTR_POP_ETH: Pop the outermost Ethernet header off the * packet. + * @OVS_ACTION_ATTR_CT_CLEAR: Clear conntrack state from the packet. * * 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 @@ -836,6 +837,7 @@ enum ovs_action_attr { OVS_ACTION_ATTR_TRUNC, /* u32 struct ovs_action_trunc. */ OVS_ACTION_ATTR_PUSH_ETH, /* struct ovs_action_push_eth. */ OVS_ACTION_ATTR_POP_ETH, /* No argument. */ + OVS_ACTION_ATTR_CT_CLEAR, /* No argument. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index a54a556fcdb5..a551232daf61 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1203,6 +1203,10 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, return err == -EINPROGRESS ? 0 : err; break; + case OVS_ACTION_ATTR_CT_CLEAR: + err = ovs_ct_clear(skb, key); + break; + case OVS_ACTION_ATTR_PUSH_ETH: err = push_eth(skb, key, nla_data(a)); break; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index d558e882ca0c..fe861e2f0deb 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1129,6 +1129,17 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, return err; } +int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) +{ + if (skb_nfct(skb)) { + nf_conntrack_put(skb_nfct(skb)); + nf_ct_set(skb, NULL, IP_CT_UNTRACKED); + ovs_ct_fill_key(skb, key); + } + + return 0; +} + static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, const struct sw_flow_key *key, bool log) { diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index bc7efd1867ab..399dfdd2c4f9 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -30,6 +30,7 @@ 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 *); +int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key); 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 *swkey, @@ -73,6 +74,12 @@ static inline int ovs_ct_execute(struct net *net, struct sk_buff *skb, return -ENOTSUPP; } +static inline int ovs_ct_clear(struct sk_buff *skb, + struct sw_flow_key *key) +{ + return -ENOTSUPP; +} + static inline void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index fc0ca9a89b8e..dc0d79092e74 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -76,6 +76,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) break; case OVS_ACTION_ATTR_CT: + case OVS_ACTION_ATTR_CT_CLEAR: case OVS_ACTION_ATTR_HASH: case OVS_ACTION_ATTR_POP_ETH: case OVS_ACTION_ATTR_POP_MPLS: @@ -2528,6 +2529,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_SAMPLE] = (u32)-1, [OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash), [OVS_ACTION_ATTR_CT] = (u32)-1, + [OVS_ACTION_ATTR_CT_CLEAR] = 0, [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, @@ -2669,6 +2671,9 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, skip_copy = true; break; + case OVS_ACTION_ATTR_CT_CLEAR: + break; + case OVS_ACTION_ATTR_PUSH_ETH: /* Disallow pushing an Ethernet header if one * is already present */ -- cgit v1.2.3 From 9354d452034273a50a4fd703bea31e5d6b1fc20b Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Thu, 2 Nov 2017 17:04:37 -0200 Subject: openvswitch: reliable interface indentification in port dumps This patch allows reliable identification of netdevice interfaces connected to openvswitch bridges. In particular, user space queries the netdev interfaces belonging to the ports for statistics, up/down state, etc. Datapath dump needs to provide enough information for the user space to be able to do that. Currently, only interface names are returned. This is not sufficient, as openvswitch allows its ports to be in different name spaces and the interface name is valid only in its name space. What is needed and generally used in other netlink APIs, is the pair ifindex+netnsid. The solution is addition of the ifindex+netnsid pair (or only ifindex if in the same name space) to vport get/dump operation. On request side, ideally the ifindex+netnsid pair could be used to get/set/del the corresponding vport. This is not implemented by this patch and can be added later if needed. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 2 ++ net/openvswitch/datapath.c | 47 +++++++++++++++++++++++++++++----------- net/openvswitch/datapath.h | 4 ++-- net/openvswitch/dp_notify.c | 4 ++-- 4 files changed, 40 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux/openvswitch.h') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index ffe397daad49..501e4c4e2a03 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -258,6 +258,8 @@ enum ovs_vport_attr { /* receiving upcalls */ OVS_VPORT_ATTR_STATS, /* struct ovs_vport_stats */ OVS_VPORT_ATTR_PAD, + OVS_VPORT_ATTR_IFINDEX, + OVS_VPORT_ATTR_NETNSID, __OVS_VPORT_ATTR_MAX }; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index c3aec6227c91..4d38ac044cee 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1848,7 +1848,8 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = { /* Called with ovs_mutex or RCU read lock. */ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, - u32 portid, u32 seq, u32 flags, u8 cmd) + struct net *net, u32 portid, u32 seq, + u32 flags, u8 cmd) { struct ovs_header *ovs_header; struct ovs_vport_stats vport_stats; @@ -1864,9 +1865,17 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, if (nla_put_u32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no) || nla_put_u32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type) || nla_put_string(skb, OVS_VPORT_ATTR_NAME, - ovs_vport_name(vport))) + ovs_vport_name(vport)) || + nla_put_u32(skb, OVS_VPORT_ATTR_IFINDEX, vport->dev->ifindex)) goto nla_put_failure; + if (!net_eq(net, dev_net(vport->dev))) { + int id = peernet2id_alloc(net, dev_net(vport->dev)); + + if (nla_put_s32(skb, OVS_VPORT_ATTR_NETNSID, id)) + goto nla_put_failure; + } + ovs_vport_get_stats(vport, &vport_stats); if (nla_put_64bit(skb, OVS_VPORT_ATTR_STATS, sizeof(struct ovs_vport_stats), &vport_stats, @@ -1896,8 +1905,8 @@ static struct sk_buff *ovs_vport_cmd_alloc_info(void) } /* Called with ovs_mutex, only via ovs_dp_notify_wq(). */ -struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid, - u32 seq, u8 cmd) +struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net, + u32 portid, u32 seq, u8 cmd) { struct sk_buff *skb; int retval; @@ -1906,7 +1915,7 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid, if (!skb) return ERR_PTR(-ENOMEM); - retval = ovs_vport_cmd_fill_info(vport, skb, portid, seq, 0, cmd); + retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd); BUG_ON(retval < 0); return skb; @@ -1920,6 +1929,8 @@ static struct vport *lookup_vport(struct net *net, struct datapath *dp; struct vport *vport; + if (a[OVS_VPORT_ATTR_IFINDEX]) + return ERR_PTR(-EOPNOTSUPP); if (a[OVS_VPORT_ATTR_NAME]) { vport = ovs_vport_locate(net, nla_data(a[OVS_VPORT_ATTR_NAME])); if (!vport) @@ -1944,6 +1955,7 @@ static struct vport *lookup_vport(struct net *net, return vport; } else return ERR_PTR(-EINVAL); + } /* Called with ovs_mutex */ @@ -1983,6 +1995,8 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] || !a[OVS_VPORT_ATTR_UPCALL_PID]) return -EINVAL; + if (a[OVS_VPORT_ATTR_IFINDEX]) + return -EOPNOTSUPP; port_no = a[OVS_VPORT_ATTR_PORT_NO] ? nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]) : 0; @@ -2032,8 +2046,9 @@ restart: goto exit_unlock_free; } - err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, - info->snd_seq, 0, OVS_VPORT_CMD_NEW); + err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), + info->snd_portid, info->snd_seq, 0, + OVS_VPORT_CMD_NEW); if (netdev_get_fwd_headroom(vport->dev) > dp->max_headroom) update_headroom(dp); @@ -2090,8 +2105,9 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) goto exit_unlock_free; } - err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, - info->snd_seq, 0, OVS_VPORT_CMD_NEW); + err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), + info->snd_portid, info->snd_seq, 0, + OVS_VPORT_CMD_NEW); BUG_ON(err < 0); ovs_unlock(); @@ -2128,8 +2144,9 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) goto exit_unlock_free; } - err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, - info->snd_seq, 0, OVS_VPORT_CMD_DEL); + err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), + info->snd_portid, info->snd_seq, 0, + OVS_VPORT_CMD_DEL); BUG_ON(err < 0); /* the vport deletion may trigger dp headroom update */ @@ -2169,8 +2186,9 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info) err = PTR_ERR(vport); if (IS_ERR(vport)) goto exit_unlock_free; - err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, - info->snd_seq, 0, OVS_VPORT_CMD_NEW); + err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), + info->snd_portid, info->snd_seq, 0, + OVS_VPORT_CMD_NEW); BUG_ON(err < 0); rcu_read_unlock(); @@ -2202,6 +2220,7 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) { if (j >= skip && ovs_vport_cmd_fill_info(vport, skb, + sock_net(skb->sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, @@ -2228,6 +2247,8 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, + [OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 }, + [OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 }, }; static const struct genl_ops dp_vport_genl_ops[] = { diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 480600649d0b..4a104ef9e12c 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -200,8 +200,8 @@ int ovs_dp_upcall(struct datapath *, struct sk_buff *, uint32_t cutlen); const char *ovs_dp_name(const struct datapath *dp); -struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq, - u8 cmd); +struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net, + u32 portid, u32 seq, u8 cmd); int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb, const struct sw_flow_actions *, struct sw_flow_key *); diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c index 653d073bae45..f3ee2f2825c0 100644 --- a/net/openvswitch/dp_notify.c +++ b/net/openvswitch/dp_notify.c @@ -30,8 +30,8 @@ static void dp_detach_port_notify(struct vport *vport) struct datapath *dp; dp = vport->dp; - notify = ovs_vport_cmd_build_info(vport, 0, 0, - OVS_VPORT_CMD_DEL); + notify = ovs_vport_cmd_build_info(vport, ovs_dp_get_net(dp), + 0, 0, OVS_VPORT_CMD_DEL); ovs_dp_detach_port(vport); if (IS_ERR(notify)) { genl_set_err(&dp_vport_genl_family, ovs_dp_get_net(dp), 0, -- cgit v1.2.3 From b2d0f5d5dc53532e6f07bc546a476a55ebdfe0f3 Mon Sep 17 00:00:00 2001 From: Yi Yang Date: Tue, 7 Nov 2017 21:07:02 +0800 Subject: openvswitch: enable NSH support v16->17 - Fixed disputed check code: keep them in nsh_push and nsh_pop but also add them in __ovs_nla_copy_actions v15->v16 - Add csum recalculation for nsh_push, nsh_pop and set_nsh pointed out by Pravin - Move nsh key into the union with ipv4 and ipv6 and add check for nsh key in match_validate pointed out by Pravin - Add nsh check in validate_set and __ovs_nla_copy_actions v14->v15 - Check size in nsh_hdr_from_nlattr - Fixed four small issues pointed out By Jiri and Eric v13->v14 - Rename skb_push_nsh to nsh_push per Dave's comment - Rename skb_pop_nsh to nsh_pop per Dave's comment v12->v13 - Fix NSH header length check in set_nsh v11->v12 - Fix missing changes old comments pointed out - Fix new comments for v11 v10->v11 - Fix the left three disputable comments for v9 but not fixed in v10. v9->v10 - Change struct ovs_key_nsh to struct ovs_nsh_key_base base; __be32 context[NSH_MD1_CONTEXT_SIZE]; - Fix new comments for v9 v8->v9 - Fix build error reported by daily intel build because nsh module isn't selected by openvswitch v7->v8 - Rework nested value and mask for OVS_KEY_ATTR_NSH - Change pop_nsh to adapt to nsh kernel module - Fix many issues per comments from Jiri Benc v6->v7 - Remove NSH GSO patches in v6 because Jiri Benc reworked it as another patch series and they have been merged. - Change it to adapt to nsh kernel module added by NSH GSO patch series v5->v6 - Fix the rest comments for v4. - Add NSH GSO support for VxLAN-gpe + NSH and Eth + NSH. v4->v5 - Fix many comments by Jiri Benc and Eric Garver for v4. v3->v4 - Add new NSH match field ttl - Update NSH header to the latest format which will be final format and won't change per its author's confirmation. - Fix comments for v3. v2->v3 - Change OVS_KEY_ATTR_NSH to nested key to handle length-fixed attributes and length-variable attriubte more flexibly. - Remove struct ovs_action_push_nsh completely - Add code to handle nested attribute for SET_MASKED - Change PUSH_NSH to use the nested OVS_KEY_ATTR_NSH to transfer NSH header data. - Fix comments and coding style issues by Jiri and Eric v1->v2 - Change encap_nsh and decap_nsh to push_nsh and pop_nsh - Dynamically allocate struct ovs_action_push_nsh for length-variable metadata. OVS master and 2.8 branch has merged NSH userspace patch series, this patch is to enable NSH support in kernel data path in order that OVS can support NSH in compat mode by porting this. Signed-off-by: Yi Yang Acked-by: Jiri Benc Acked-by: Eric Garver Acked-by: Pravin Shelar Signed-off-by: David S. Miller --- include/net/nsh.h | 3 + include/uapi/linux/openvswitch.h | 29 ++++ net/nsh/nsh.c | 60 +++++++ net/openvswitch/Kconfig | 1 + net/openvswitch/actions.c | 116 +++++++++++++ net/openvswitch/flow.c | 51 ++++++ net/openvswitch/flow.h | 7 + net/openvswitch/flow_netlink.c | 343 ++++++++++++++++++++++++++++++++++++++- net/openvswitch/flow_netlink.h | 5 + 9 files changed, 613 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux/openvswitch.h') diff --git a/include/net/nsh.h b/include/net/nsh.h index a1eaea20be96..350b1ad11c7f 100644 --- a/include/net/nsh.h +++ b/include/net/nsh.h @@ -304,4 +304,7 @@ static inline void nsh_set_flags_ttl_len(struct nshhdr *nsh, u8 flags, NSH_FLAGS_MASK | NSH_TTL_MASK | NSH_LEN_MASK); } +int nsh_push(struct sk_buff *skb, const struct nshhdr *pushed_nh); +int nsh_pop(struct sk_buff *skb); + #endif /* __NET_NSH_H */ diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 501e4c4e2a03..ec75a685f1dd 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -336,6 +336,7 @@ enum ovs_key_attr { OVS_KEY_ATTR_CT_LABELS, /* 16-octet connection tracking label */ OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, /* struct ovs_key_ct_tuple_ipv4 */ OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, /* struct ovs_key_ct_tuple_ipv6 */ + OVS_KEY_ATTR_NSH, /* Nested set of ovs_nsh_key_* */ #ifdef __KERNEL__ OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */ @@ -495,6 +496,30 @@ struct ovs_key_ct_tuple_ipv6 { __u8 ipv6_proto; }; +enum ovs_nsh_key_attr { + OVS_NSH_KEY_ATTR_UNSPEC, + OVS_NSH_KEY_ATTR_BASE, /* struct ovs_nsh_key_base. */ + OVS_NSH_KEY_ATTR_MD1, /* struct ovs_nsh_key_md1. */ + OVS_NSH_KEY_ATTR_MD2, /* variable-length octets for MD type 2. */ + __OVS_NSH_KEY_ATTR_MAX +}; + +#define OVS_NSH_KEY_ATTR_MAX (__OVS_NSH_KEY_ATTR_MAX - 1) + +struct ovs_nsh_key_base { + __u8 flags; + __u8 ttl; + __u8 mdtype; + __u8 np; + __be32 path_hdr; +}; + +#define NSH_MD1_CONTEXT_SIZE 4 + +struct ovs_nsh_key_md1 { + __be32 context[NSH_MD1_CONTEXT_SIZE]; +}; + /** * enum ovs_flow_attr - attributes for %OVS_FLOW_* commands. * @OVS_FLOW_ATTR_KEY: Nested %OVS_KEY_ATTR_* attributes specifying the flow @@ -811,6 +836,8 @@ struct ovs_action_push_eth { * @OVS_ACTION_ATTR_POP_ETH: Pop the outermost Ethernet header off the * packet. * @OVS_ACTION_ATTR_CT_CLEAR: Clear conntrack state from the packet. + * @OVS_ACTION_ATTR_PUSH_NSH: push NSH header to the packet. + * @OVS_ACTION_ATTR_POP_NSH: pop the outermost NSH header off the packet. * * 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 @@ -841,6 +868,8 @@ enum ovs_action_attr { OVS_ACTION_ATTR_PUSH_ETH, /* struct ovs_action_push_eth. */ OVS_ACTION_ATTR_POP_ETH, /* No argument. */ OVS_ACTION_ATTR_CT_CLEAR, /* No argument. */ + OVS_ACTION_ATTR_PUSH_NSH, /* Nested OVS_NSH_KEY_ATTR_*. */ + OVS_ACTION_ATTR_POP_NSH, /* No argument. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index 58fb827439a8..d7da99a0b0b8 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -14,6 +14,66 @@ #include #include +int nsh_push(struct sk_buff *skb, const struct nshhdr *pushed_nh) +{ + struct nshhdr *nh; + size_t length = nsh_hdr_len(pushed_nh); + u8 next_proto; + + if (skb->mac_len) { + next_proto = TUN_P_ETHERNET; + } else { + next_proto = tun_p_from_eth_p(skb->protocol); + if (!next_proto) + return -EAFNOSUPPORT; + } + + /* Add the NSH header */ + if (skb_cow_head(skb, length) < 0) + return -ENOMEM; + + skb_push(skb, length); + nh = (struct nshhdr *)(skb->data); + memcpy(nh, pushed_nh, length); + nh->np = next_proto; + skb_postpush_rcsum(skb, nh, length); + + skb->protocol = htons(ETH_P_NSH); + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_mac_len(skb); + + return 0; +} +EXPORT_SYMBOL_GPL(nsh_push); + +int nsh_pop(struct sk_buff *skb) +{ + struct nshhdr *nh; + size_t length; + __be16 inner_proto; + + if (!pskb_may_pull(skb, NSH_BASE_HDR_LEN)) + return -ENOMEM; + nh = (struct nshhdr *)(skb->data); + length = nsh_hdr_len(nh); + inner_proto = tun_p_to_eth_p(nh->np); + if (!pskb_may_pull(skb, length)) + return -ENOMEM; + + if (!inner_proto) + return -EAFNOSUPPORT; + + skb_pull_rcsum(skb, length); + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_mac_len(skb); + skb->protocol = inner_proto; + + return 0; +} +EXPORT_SYMBOL_GPL(nsh_pop); + static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, netdev_features_t features) { diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index ce947292ae77..2650205cdaf9 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -14,6 +14,7 @@ config OPENVSWITCH select MPLS select NET_MPLS_GSO select DST_CACHE + select NET_NSH ---help--- Open vSwitch is a multilayer Ethernet switch targeted at virtualized environments. In addition to supporting a variety of features diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index a551232daf61..9a6a6d51e421 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -43,6 +43,7 @@ #include "flow.h" #include "conntrack.h" #include "vport.h" +#include "flow_netlink.h" struct deferred_action { struct sk_buff *skb; @@ -380,6 +381,38 @@ static int push_eth(struct sk_buff *skb, struct sw_flow_key *key, return 0; } +static int push_nsh(struct sk_buff *skb, struct sw_flow_key *key, + const struct nshhdr *nh) +{ + int err; + + err = nsh_push(skb, nh); + if (err) + return err; + + /* safe right before invalidate_flow_key */ + key->mac_proto = MAC_PROTO_NONE; + invalidate_flow_key(key); + return 0; +} + +static int pop_nsh(struct sk_buff *skb, struct sw_flow_key *key) +{ + int err; + + err = nsh_pop(skb); + if (err) + return err; + + /* safe right before invalidate_flow_key */ + if (skb->protocol == htons(ETH_P_TEB)) + key->mac_proto = MAC_PROTO_ETHERNET; + else + key->mac_proto = MAC_PROTO_NONE; + invalidate_flow_key(key); + return 0; +} + static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh, __be32 addr, __be32 new_addr) { @@ -602,6 +635,69 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } +static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key, + const struct nlattr *a) +{ + struct nshhdr *nh; + size_t length; + int err; + u8 flags; + u8 ttl; + int i; + + struct ovs_key_nsh key; + struct ovs_key_nsh mask; + + err = nsh_key_from_nlattr(a, &key, &mask); + if (err) + return err; + + /* Make sure the NSH base header is there */ + if (!pskb_may_pull(skb, skb_network_offset(skb) + NSH_BASE_HDR_LEN)) + return -ENOMEM; + + nh = nsh_hdr(skb); + length = nsh_hdr_len(nh); + + /* Make sure the whole NSH header is there */ + err = skb_ensure_writable(skb, skb_network_offset(skb) + + length); + if (unlikely(err)) + return err; + + nh = nsh_hdr(skb); + skb_postpull_rcsum(skb, nh, length); + flags = nsh_get_flags(nh); + flags = OVS_MASKED(flags, key.base.flags, mask.base.flags); + flow_key->nsh.base.flags = flags; + ttl = nsh_get_ttl(nh); + ttl = OVS_MASKED(ttl, key.base.ttl, mask.base.ttl); + flow_key->nsh.base.ttl = ttl; + nsh_set_flags_and_ttl(nh, flags, ttl); + nh->path_hdr = OVS_MASKED(nh->path_hdr, key.base.path_hdr, + mask.base.path_hdr); + flow_key->nsh.base.path_hdr = nh->path_hdr; + switch (nh->mdtype) { + case NSH_M_TYPE1: + for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) { + nh->md1.context[i] = + OVS_MASKED(nh->md1.context[i], key.context[i], + mask.context[i]); + } + memcpy(flow_key->nsh.context, nh->md1.context, + sizeof(nh->md1.context)); + break; + case NSH_M_TYPE2: + memset(flow_key->nsh.context, 0, + sizeof(flow_key->nsh.context)); + break; + default: + return -EINVAL; + } + skb_postpush_rcsum(skb, nh, length); + return 0; +} + /* Must follow skb_ensure_writable() since that can move the skb data. */ static void set_tp_port(struct sk_buff *skb, __be16 *port, __be16 new_port, __sum16 *check) @@ -1024,6 +1120,10 @@ static int execute_masked_set_action(struct sk_buff *skb, get_mask(a, struct ovs_key_ethernet *)); break; + case OVS_KEY_ATTR_NSH: + err = set_nsh(skb, flow_key, a); + break; + case OVS_KEY_ATTR_IPV4: err = set_ipv4(skb, flow_key, nla_data(a), get_mask(a, struct ovs_key_ipv4 *)); @@ -1214,6 +1314,22 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, case OVS_ACTION_ATTR_POP_ETH: err = pop_eth(skb, key); break; + + case OVS_ACTION_ATTR_PUSH_NSH: { + u8 buffer[NSH_HDR_MAX_LEN]; + struct nshhdr *nh = (struct nshhdr *)buffer; + + err = nsh_hdr_from_nlattr(nla_data(a), nh, + NSH_HDR_MAX_LEN); + if (unlikely(err)) + break; + err = push_nsh(skb, key, nh); + break; + } + + case OVS_ACTION_ATTR_POP_NSH: + err = pop_nsh(skb, key); + break; } if (unlikely(err)) { diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 8c94cef25a72..864ddb1e3642 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -46,6 +46,7 @@ #include #include #include +#include #include "conntrack.h" #include "datapath.h" @@ -490,6 +491,52 @@ invalid: return 0; } +static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key) +{ + struct nshhdr *nh; + unsigned int nh_ofs = skb_network_offset(skb); + u8 version, length; + int err; + + err = check_header(skb, nh_ofs + NSH_BASE_HDR_LEN); + if (unlikely(err)) + return err; + + nh = nsh_hdr(skb); + version = nsh_get_ver(nh); + length = nsh_hdr_len(nh); + + if (version != 0) + return -EINVAL; + + err = check_header(skb, nh_ofs + length); + if (unlikely(err)) + return err; + + nh = nsh_hdr(skb); + key->nsh.base.flags = nsh_get_flags(nh); + key->nsh.base.ttl = nsh_get_ttl(nh); + key->nsh.base.mdtype = nh->mdtype; + key->nsh.base.np = nh->np; + key->nsh.base.path_hdr = nh->path_hdr; + switch (key->nsh.base.mdtype) { + case NSH_M_TYPE1: + if (length != NSH_M_TYPE1_LEN) + return -EINVAL; + memcpy(key->nsh.context, nh->md1.context, + sizeof(nh->md1)); + break; + case NSH_M_TYPE2: + memset(key->nsh.context, 0, + sizeof(nh->md1)); + break; + default: + return -EINVAL; + } + + return 0; +} + /** * key_extract - extracts a flow key from an Ethernet frame. * @skb: sk_buff that contains the frame, with skb->data pointing to the @@ -735,6 +782,10 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) memset(&key->tp, 0, sizeof(key->tp)); } } + } else if (key->eth.type == htons(ETH_P_NSH)) { + error = parse_nsh(skb, key); + if (error) + return error; } return 0; } diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 1875bba4f865..c670dd24b8b7 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -35,6 +35,7 @@ #include #include #include +#include struct sk_buff; @@ -66,6 +67,11 @@ struct vlan_head { (offsetof(struct sw_flow_key, recirc_id) + \ FIELD_SIZEOF(struct sw_flow_key, recirc_id)) +struct ovs_key_nsh { + struct ovs_nsh_key_base base; + __be32 context[NSH_MD1_CONTEXT_SIZE]; +}; + struct sw_flow_key { u8 tun_opts[IP_TUNNEL_OPTS_MAX]; u8 tun_opts_len; @@ -143,6 +149,7 @@ struct sw_flow_key { } nd; }; } ipv6; + struct ovs_key_nsh nsh; /* network service header */ }; struct { /* Connection tracking fields not packed above. */ diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index dc0d79092e74..4201f9293af3 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -48,6 +48,7 @@ #include #include #include +#include #include #include "flow_netlink.h" @@ -80,9 +81,11 @@ static bool actions_may_change_flow(const struct nlattr *actions) case OVS_ACTION_ATTR_HASH: case OVS_ACTION_ATTR_POP_ETH: case OVS_ACTION_ATTR_POP_MPLS: + case OVS_ACTION_ATTR_POP_NSH: case OVS_ACTION_ATTR_POP_VLAN: case OVS_ACTION_ATTR_PUSH_ETH: case OVS_ACTION_ATTR_PUSH_MPLS: + case OVS_ACTION_ATTR_PUSH_NSH: case OVS_ACTION_ATTR_PUSH_VLAN: case OVS_ACTION_ATTR_SAMPLE: case OVS_ACTION_ATTR_SET: @@ -175,7 +178,8 @@ static bool match_validate(const struct sw_flow_match *match, | (1 << OVS_KEY_ATTR_ICMPV6) | (1 << OVS_KEY_ATTR_ARP) | (1 << OVS_KEY_ATTR_ND) - | (1 << OVS_KEY_ATTR_MPLS)); + | (1 << OVS_KEY_ATTR_MPLS) + | (1 << OVS_KEY_ATTR_NSH)); /* Always allowed mask fields. */ mask_allowed |= ((1 << OVS_KEY_ATTR_TUNNEL) @@ -284,6 +288,14 @@ static bool match_validate(const struct sw_flow_match *match, } } + if (match->key->eth.type == htons(ETH_P_NSH)) { + key_expected |= 1 << OVS_KEY_ATTR_NSH; + if (match->mask && + match->mask->key.eth.type == htons(0xffff)) { + mask_allowed |= 1 << OVS_KEY_ATTR_NSH; + } + } + if ((key_attrs & key_expected) != key_expected) { /* Key attributes check failed. */ OVS_NLERR(log, "Missing key (keys=%llx, expected=%llx)", @@ -325,12 +337,25 @@ size_t ovs_tun_key_attr_size(void) + nla_total_size(4); /* OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS */ } +size_t ovs_nsh_key_attr_size(void) +{ + /* Whenever adding new OVS_NSH_KEY_ FIELDS, we should consider + * updating this function. + */ + return nla_total_size(NSH_BASE_HDR_LEN) /* OVS_NSH_KEY_ATTR_BASE */ + /* OVS_NSH_KEY_ATTR_MD1 and OVS_NSH_KEY_ATTR_MD2 are + * mutually exclusive, so the bigger one can cover + * the small one. + */ + + nla_total_size(NSH_CTX_HDRS_MAX_LEN); +} + size_t ovs_key_attr_size(void) { /* Whenever adding new OVS_KEY_ FIELDS, we should consider * updating this function. */ - BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 28); + BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 29); return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */ + nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */ @@ -344,6 +369,8 @@ size_t ovs_key_attr_size(void) + nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */ + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */ + nla_total_size(40) /* OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6 */ + + nla_total_size(0) /* OVS_KEY_ATTR_NSH */ + + ovs_nsh_key_attr_size() + nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */ + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */ + nla_total_size(4) /* OVS_KEY_ATTR_VLAN */ @@ -377,6 +404,13 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] [OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS] = { .len = sizeof(u32) }, }; +static const struct ovs_len_tbl +ovs_nsh_key_attr_lens[OVS_NSH_KEY_ATTR_MAX + 1] = { + [OVS_NSH_KEY_ATTR_BASE] = { .len = sizeof(struct ovs_nsh_key_base) }, + [OVS_NSH_KEY_ATTR_MD1] = { .len = sizeof(struct ovs_nsh_key_md1) }, + [OVS_NSH_KEY_ATTR_MD2] = { .len = OVS_ATTR_VARIABLE }, +}; + /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { [OVS_KEY_ATTR_ENCAP] = { .len = OVS_ATTR_NESTED }, @@ -409,6 +443,8 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { .len = sizeof(struct ovs_key_ct_tuple_ipv4) }, [OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6] = { .len = sizeof(struct ovs_key_ct_tuple_ipv6) }, + [OVS_KEY_ATTR_NSH] = { .len = OVS_ATTR_NESTED, + .next = ovs_nsh_key_attr_lens, }, }; static bool check_attr_len(unsigned int attr_len, unsigned int expected_len) @@ -1227,6 +1263,221 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, return 0; } +int nsh_hdr_from_nlattr(const struct nlattr *attr, + struct nshhdr *nh, size_t size) +{ + struct nlattr *a; + int rem; + u8 flags = 0; + u8 ttl = 0; + int mdlen = 0; + + /* validate_nsh has check this, so we needn't do duplicate check here + */ + if (size < NSH_BASE_HDR_LEN) + return -ENOBUFS; + + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); + + switch (type) { + case OVS_NSH_KEY_ATTR_BASE: { + const struct ovs_nsh_key_base *base = nla_data(a); + + flags = base->flags; + ttl = base->ttl; + nh->np = base->np; + nh->mdtype = base->mdtype; + nh->path_hdr = base->path_hdr; + break; + } + case OVS_NSH_KEY_ATTR_MD1: + mdlen = nla_len(a); + if (mdlen > size - NSH_BASE_HDR_LEN) + return -ENOBUFS; + memcpy(&nh->md1, nla_data(a), mdlen); + break; + + case OVS_NSH_KEY_ATTR_MD2: + mdlen = nla_len(a); + if (mdlen > size - NSH_BASE_HDR_LEN) + return -ENOBUFS; + memcpy(&nh->md2, nla_data(a), mdlen); + break; + + default: + return -EINVAL; + } + } + + /* nsh header length = NSH_BASE_HDR_LEN + mdlen */ + nh->ver_flags_ttl_len = 0; + nsh_set_flags_ttl_len(nh, flags, ttl, NSH_BASE_HDR_LEN + mdlen); + + return 0; +} + +int nsh_key_from_nlattr(const struct nlattr *attr, + struct ovs_key_nsh *nsh, struct ovs_key_nsh *nsh_mask) +{ + struct nlattr *a; + int rem; + + /* validate_nsh has check this, so we needn't do duplicate check here + */ + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); + + switch (type) { + case OVS_NSH_KEY_ATTR_BASE: { + const struct ovs_nsh_key_base *base = nla_data(a); + const struct ovs_nsh_key_base *base_mask = base + 1; + + nsh->base = *base; + nsh_mask->base = *base_mask; + break; + } + case OVS_NSH_KEY_ATTR_MD1: { + const struct ovs_nsh_key_md1 *md1 = nla_data(a); + const struct ovs_nsh_key_md1 *md1_mask = md1 + 1; + + memcpy(nsh->context, md1->context, sizeof(*md1)); + memcpy(nsh_mask->context, md1_mask->context, + sizeof(*md1_mask)); + break; + } + case OVS_NSH_KEY_ATTR_MD2: + /* Not supported yet */ + return -ENOTSUPP; + default: + return -EINVAL; + } + } + + return 0; +} + +static int nsh_key_put_from_nlattr(const struct nlattr *attr, + struct sw_flow_match *match, bool is_mask, + bool is_push_nsh, bool log) +{ + struct nlattr *a; + int rem; + bool has_base = false; + bool has_md1 = false; + bool has_md2 = false; + u8 mdtype = 0; + int mdlen = 0; + + if (WARN_ON(is_push_nsh && is_mask)) + return -EINVAL; + + nla_for_each_nested(a, attr, rem) { + int type = nla_type(a); + int i; + + if (type > OVS_NSH_KEY_ATTR_MAX) { + OVS_NLERR(log, "nsh attr %d is out of range max %d", + type, OVS_NSH_KEY_ATTR_MAX); + return -EINVAL; + } + + if (!check_attr_len(nla_len(a), + ovs_nsh_key_attr_lens[type].len)) { + OVS_NLERR( + log, + "nsh attr %d has unexpected len %d expected %d", + type, + nla_len(a), + ovs_nsh_key_attr_lens[type].len + ); + return -EINVAL; + } + + switch (type) { + case OVS_NSH_KEY_ATTR_BASE: { + const struct ovs_nsh_key_base *base = nla_data(a); + + has_base = true; + mdtype = base->mdtype; + SW_FLOW_KEY_PUT(match, nsh.base.flags, + base->flags, is_mask); + SW_FLOW_KEY_PUT(match, nsh.base.ttl, + base->ttl, is_mask); + SW_FLOW_KEY_PUT(match, nsh.base.mdtype, + base->mdtype, is_mask); + SW_FLOW_KEY_PUT(match, nsh.base.np, + base->np, is_mask); + SW_FLOW_KEY_PUT(match, nsh.base.path_hdr, + base->path_hdr, is_mask); + break; + } + case OVS_NSH_KEY_ATTR_MD1: { + const struct ovs_nsh_key_md1 *md1 = nla_data(a); + + has_md1 = true; + for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) + SW_FLOW_KEY_PUT(match, nsh.context[i], + md1->context[i], is_mask); + break; + } + case OVS_NSH_KEY_ATTR_MD2: + if (!is_push_nsh) /* Not supported MD type 2 yet */ + return -ENOTSUPP; + + has_md2 = true; + mdlen = nla_len(a); + if (mdlen > NSH_CTX_HDRS_MAX_LEN || mdlen <= 0) { + OVS_NLERR( + log, + "Invalid MD length %d for MD type %d", + mdlen, + mdtype + ); + return -EINVAL; + } + break; + default: + OVS_NLERR(log, "Unknown nsh attribute %d", + type); + return -EINVAL; + } + } + + if (rem > 0) { + OVS_NLERR(log, "nsh attribute has %d unknown bytes.", rem); + return -EINVAL; + } + + if (has_md1 && has_md2) { + OVS_NLERR( + 1, + "invalid nsh attribute: md1 and md2 are exclusive." + ); + return -EINVAL; + } + + if (!is_mask) { + if ((has_md1 && mdtype != NSH_M_TYPE1) || + (has_md2 && mdtype != NSH_M_TYPE2)) { + OVS_NLERR(1, "nsh attribute has unmatched MD type %d.", + mdtype); + return -EINVAL; + } + + if (is_push_nsh && + (!has_base || (!has_md1 && !has_md2))) { + OVS_NLERR( + 1, + "push_nsh: missing base or metadata attributes" + ); + return -EINVAL; + } + } + + return 0; +} + static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match, u64 attrs, const struct nlattr **a, bool is_mask, bool log) @@ -1354,6 +1605,13 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match, attrs &= ~(1 << OVS_KEY_ATTR_ARP); } + if (attrs & (1 << OVS_KEY_ATTR_NSH)) { + if (nsh_key_put_from_nlattr(a[OVS_KEY_ATTR_NSH], match, + is_mask, false, log) < 0) + return -EINVAL; + attrs &= ~(1 << OVS_KEY_ATTR_NSH); + } + if (attrs & (1 << OVS_KEY_ATTR_MPLS)) { const struct ovs_key_mpls *mpls_key; @@ -1670,6 +1928,34 @@ static int ovs_nla_put_vlan(struct sk_buff *skb, const struct vlan_head *vh, return 0; } +static int nsh_key_to_nlattr(const struct ovs_key_nsh *nsh, bool is_mask, + struct sk_buff *skb) +{ + struct nlattr *start; + + start = nla_nest_start(skb, OVS_KEY_ATTR_NSH); + if (!start) + return -EMSGSIZE; + + if (nla_put(skb, OVS_NSH_KEY_ATTR_BASE, sizeof(nsh->base), &nsh->base)) + goto nla_put_failure; + + if (is_mask || nsh->base.mdtype == NSH_M_TYPE1) { + if (nla_put(skb, OVS_NSH_KEY_ATTR_MD1, + sizeof(nsh->context), nsh->context)) + goto nla_put_failure; + } + + /* Don't support MD type 2 yet */ + + nla_nest_end(skb, start); + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + static int __ovs_nla_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, bool is_mask, struct sk_buff *skb) @@ -1798,6 +2084,9 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, ipv6_key->ipv6_tclass = output->ip.tos; ipv6_key->ipv6_hlimit = output->ip.ttl; ipv6_key->ipv6_frag = output->ip.frag; + } else if (swkey->eth.type == htons(ETH_P_NSH)) { + if (nsh_key_to_nlattr(&output->nsh, is_mask, skb)) + goto nla_put_failure; } else if (swkey->eth.type == htons(ETH_P_ARP) || swkey->eth.type == htons(ETH_P_RARP)) { struct ovs_key_arp *arp_key; @@ -2292,6 +2581,19 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, return err; } +static bool validate_nsh(const struct nlattr *attr, bool is_mask, + bool is_push_nsh, bool log) +{ + struct sw_flow_match match; + struct sw_flow_key key; + int ret = 0; + + ovs_match_init(&match, &key, true, NULL); + ret = nsh_key_put_from_nlattr(attr, &match, is_mask, + is_push_nsh, log); + return !ret; +} + /* Return false if there are any non-masked bits set. * Mask follows data immediately, before any netlink padding. */ @@ -2434,6 +2736,13 @@ static int validate_set(const struct nlattr *a, break; + case OVS_KEY_ATTR_NSH: + if (eth_type != htons(ETH_P_NSH)) + return -EINVAL; + if (!validate_nsh(nla_data(a), masked, false, log)) + return -EINVAL; + break; + default: return -EINVAL; } @@ -2533,6 +2842,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [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, + [OVS_ACTION_ATTR_PUSH_NSH] = (u32)-1, + [OVS_ACTION_ATTR_POP_NSH] = 0, }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -2690,6 +3001,34 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, mac_proto = MAC_PROTO_ETHERNET; break; + case OVS_ACTION_ATTR_PUSH_NSH: + if (mac_proto != MAC_PROTO_ETHERNET) { + u8 next_proto; + + next_proto = tun_p_from_eth_p(eth_type); + if (!next_proto) + return -EINVAL; + } + mac_proto = MAC_PROTO_NONE; + if (!validate_nsh(nla_data(a), false, true, true)) + return -EINVAL; + break; + + case OVS_ACTION_ATTR_POP_NSH: { + __be16 inner_proto; + + if (eth_type != htons(ETH_P_NSH)) + return -EINVAL; + inner_proto = tun_p_to_eth_p(key->nsh.base.np); + if (!inner_proto) + return -EINVAL; + if (key->nsh.base.np == TUN_P_ETHERNET) + mac_proto = MAC_PROTO_ETHERNET; + else + mac_proto = MAC_PROTO_NONE; + break; + } + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index 929c665ac3aa..6657606b2b47 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -79,4 +79,9 @@ int ovs_nla_put_actions(const struct nlattr *attr, void ovs_nla_free_flow_actions(struct sw_flow_actions *); void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *); +int nsh_key_from_nlattr(const struct nlattr *attr, struct ovs_key_nsh *nsh, + struct ovs_key_nsh *nsh_mask); +int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh, + size_t size); + #endif /* flow_netlink.h */ -- cgit v1.2.3 From 5794040647de4011598a6d005fdad95d24fd385b Mon Sep 17 00:00:00 2001 From: Andy Zhou Date: Fri, 10 Nov 2017 12:09:40 -0800 Subject: openvswitch: Add meter netlink definitions Meter has its own netlink family. Define netlink messages and attributes for communicating with the user space programs. Signed-off-by: Andy Zhou Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 51 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) (limited to 'include/uapi/linux/openvswitch.h') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index ec75a685f1dd..d60b9a4cf3d1 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -883,4 +883,55 @@ enum ovs_action_attr { #define OVS_ACTION_ATTR_MAX (__OVS_ACTION_ATTR_MAX - 1) +/* Meters. */ +#define OVS_METER_FAMILY "ovs_meter" +#define OVS_METER_MCGROUP "ovs_meter" +#define OVS_METER_VERSION 0x1 + +enum ovs_meter_cmd { + OVS_METER_CMD_UNSPEC, + OVS_METER_CMD_FEATURES, /* Get features supported by the datapath. */ + OVS_METER_CMD_SET, /* Add or modify a meter. */ + OVS_METER_CMD_DEL, /* Delete a meter. */ + OVS_METER_CMD_GET /* Get meter stats. */ +}; + +enum ovs_meter_attr { + OVS_METER_ATTR_UNSPEC, + OVS_METER_ATTR_ID, /* u32 meter ID within datapath. */ + OVS_METER_ATTR_KBPS, /* No argument. If set, units in kilobits + * per second. Otherwise, units in + * packets per second. + */ + OVS_METER_ATTR_STATS, /* struct ovs_flow_stats for the meter. */ + OVS_METER_ATTR_BANDS, /* Nested attributes for meter bands. */ + OVS_METER_ATTR_USED, /* u64 msecs last used in monotonic time. */ + OVS_METER_ATTR_CLEAR, /* Flag to clear stats, used. */ + OVS_METER_ATTR_MAX_METERS, /* u32 number of meters supported. */ + OVS_METER_ATTR_MAX_BANDS, /* u32 max number of bands per meter. */ + OVS_METER_ATTR_PAD, + __OVS_METER_ATTR_MAX +}; + +#define OVS_METER_ATTR_MAX (__OVS_METER_ATTR_MAX - 1) + +enum ovs_band_attr { + OVS_BAND_ATTR_UNSPEC, + OVS_BAND_ATTR_TYPE, /* u32 OVS_METER_BAND_TYPE_* constant. */ + OVS_BAND_ATTR_RATE, /* u32 band rate in meter units (see above). */ + OVS_BAND_ATTR_BURST, /* u32 burst size in meter units. */ + OVS_BAND_ATTR_STATS, /* struct ovs_flow_stats for the band. */ + __OVS_BAND_ATTR_MAX +}; + +#define OVS_BAND_ATTR_MAX (__OVS_BAND_ATTR_MAX - 1) + +enum ovs_meter_band_type { + OVS_METER_BAND_TYPE_UNSPEC, + OVS_METER_BAND_TYPE_DROP, /* Drop exceeding packets. */ + __OVS_METER_BAND_TYPE_MAX +}; + +#define OVS_METER_BAND_TYPE_MAX (__OVS_METER_BAND_TYPE_MAX - 1) + #endif /* _LINUX_OPENVSWITCH_H */ -- cgit v1.2.3 From cd8a6c33693c1b89d2737ffdbf9611564e9ac907 Mon Sep 17 00:00:00 2001 From: Andy Zhou Date: Fri, 10 Nov 2017 12:09:43 -0800 Subject: openvswitch: Add meter action support Implements OVS kernel meter action support. Signed-off-by: Andy Zhou Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 3 +++ net/openvswitch/actions.c | 6 ++++++ net/openvswitch/datapath.h | 1 + net/openvswitch/flow_netlink.c | 6 ++++++ 4 files changed, 16 insertions(+) (limited to 'include/uapi/linux/openvswitch.h') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index d60b9a4cf3d1..4265d7f9e1f2 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -838,6 +838,8 @@ struct ovs_action_push_eth { * @OVS_ACTION_ATTR_CT_CLEAR: Clear conntrack state from the packet. * @OVS_ACTION_ATTR_PUSH_NSH: push NSH header to the packet. * @OVS_ACTION_ATTR_POP_NSH: pop the outermost NSH header off the packet. + * @OVS_ACTION_ATTR_METER: Run packet through a meter, which may drop the + * packet, or modify the packet (e.g., change the DSCP field). * * 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 @@ -870,6 +872,7 @@ enum ovs_action_attr { OVS_ACTION_ATTR_CT_CLEAR, /* No argument. */ OVS_ACTION_ATTR_PUSH_NSH, /* Nested OVS_NSH_KEY_ATTR_*. */ OVS_ACTION_ATTR_POP_NSH, /* No argument. */ + OVS_ACTION_ATTR_METER, /* u32 meter ID. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 9a6a6d51e421..30a5df27116e 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1330,6 +1330,12 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, case OVS_ACTION_ATTR_POP_NSH: err = pop_nsh(skb, key); break; + + case OVS_ACTION_ATTR_METER: + if (ovs_meter_execute(dp, skb, key, nla_get_u32(a))) { + consume_skb(skb); + return 0; + } } if (unlikely(err)) { diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 5d2997b42460..523d65526766 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -30,6 +30,7 @@ #include "conntrack.h" #include "flow.h" #include "flow_table.h" +#include "meter.h" #include "vport-internal_dev.h" #define DP_MAX_PORTS USHRT_MAX diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 4201f9293af3..bb4dae198c78 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -90,6 +90,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) case OVS_ACTION_ATTR_SAMPLE: case OVS_ACTION_ATTR_SET: case OVS_ACTION_ATTR_SET_MASKED: + case OVS_ACTION_ATTR_METER: default: return true; } @@ -2844,6 +2845,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_POP_ETH] = 0, [OVS_ACTION_ATTR_PUSH_NSH] = (u32)-1, [OVS_ACTION_ATTR_POP_NSH] = 0, + [OVS_ACTION_ATTR_METER] = sizeof(u32), }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -3029,6 +3031,10 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, break; } + case OVS_ACTION_ATTR_METER: + /* Non-existent meters are simply ignored. */ + break; + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; -- cgit v1.2.3