diff options
Diffstat (limited to 'net/openvswitch')
| -rw-r--r-- | net/openvswitch/actions.c | 7 | ||||
| -rw-r--r-- | net/openvswitch/datapath.c | 8 | ||||
| -rw-r--r-- | net/openvswitch/flow.c | 9 | ||||
| -rw-r--r-- | net/openvswitch/flow.h | 14 | ||||
| -rw-r--r-- | net/openvswitch/flow_netlink.c | 299 | ||||
| -rw-r--r-- | net/openvswitch/vport-geneve.c | 33 | ||||
| -rw-r--r-- | net/openvswitch/vport-gre.c | 32 | ||||
| -rw-r--r-- | net/openvswitch/vport-vxlan.c | 105 | ||||
| -rw-r--r-- | net/openvswitch/vport-vxlan.h | 11 | ||||
| -rw-r--r-- | net/openvswitch/vport.c | 17 | ||||
| -rw-r--r-- | net/openvswitch/vport.h | 18 |
11 files changed, 368 insertions, 185 deletions
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 764fdc39c63b..b4cffe686126 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -147,7 +147,8 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key, hdr = eth_hdr(skb); hdr->h_proto = mpls->mpls_ethertype; - skb_set_inner_protocol(skb, skb->protocol); + if (!skb->inner_protocol) + skb_set_inner_protocol(skb, skb->protocol); skb->protocol = mpls->mpls_ethertype; invalidate_flow_key(key); @@ -211,7 +212,7 @@ static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key) int err; err = skb_vlan_pop(skb); - if (vlan_tx_tag_present(skb)) + if (skb_vlan_tag_present(skb)) invalidate_flow_key(key); else key->eth.tci = 0; @@ -221,7 +222,7 @@ static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key) static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key, const struct ovs_action_push_vlan *vlan) { - if (vlan_tx_tag_present(skb)) + if (skb_vlan_tag_present(skb)) invalidate_flow_key(key); else key->eth.tci = vlan->vlan_tci; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 332b5a031739..8bda3cc12344 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -83,8 +83,7 @@ static bool ovs_must_notify(struct genl_family *family, struct genl_info *info, unsigned int group) { return info->nlhdr->nlmsg_flags & NLM_F_ECHO || - genl_has_listeners(family, genl_info_net(info)->genl_sock, - group); + genl_has_listeners(family, genl_info_net(info), group); } static void ovs_notify(struct genl_family *family, @@ -420,7 +419,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, if (!dp_ifindex) return -ENODEV; - if (vlan_tx_tag_present(skb)) { + if (skb_vlan_tag_present(skb)) { nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; @@ -525,7 +524,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info) struct vport *input_vport; int len; int err; - bool log = !a[OVS_FLOW_ATTR_PROBE]; + bool log = !a[OVS_PACKET_ATTR_PROBE]; err = -EINVAL; if (!a[OVS_PACKET_ATTR_PACKET] || !a[OVS_PACKET_ATTR_KEY] || @@ -611,6 +610,7 @@ static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = { [OVS_PACKET_ATTR_PACKET] = { .len = ETH_HLEN }, [OVS_PACKET_ATTR_KEY] = { .type = NLA_NESTED }, [OVS_PACKET_ATTR_ACTIONS] = { .type = NLA_NESTED }, + [OVS_PACKET_ATTR_PROBE] = { .type = NLA_FLAG }, }; static const struct genl_ops dp_packet_genl_ops[] = { diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 70bef2ab7f2b..e2c348b8baca 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -70,6 +70,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, { struct flow_stats *stats; int node = numa_node_id(); + int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); stats = rcu_dereference(flow->stats[node]); @@ -105,7 +106,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, if (likely(new_stats)) { new_stats->used = jiffies; new_stats->packet_count = 1; - new_stats->byte_count = skb->len; + new_stats->byte_count = len; new_stats->tcp_flags = tcp_flags; spin_lock_init(&new_stats->lock); @@ -120,7 +121,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, stats->used = jiffies; stats->packet_count++; - stats->byte_count += skb->len; + stats->byte_count += len; stats->tcp_flags |= tcp_flags; unlock: spin_unlock(&stats->lock); @@ -471,7 +472,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) */ key->eth.tci = 0; - if (vlan_tx_tag_present(skb)) + if (skb_vlan_tag_present(skb)) key->eth.tci = htons(skb->vlan_tci); else if (eth->h_proto == htons(ETH_P_8021Q)) if (unlikely(parse_vlan(skb, key))) @@ -690,7 +691,7 @@ int ovs_flow_key_extract(const struct ovs_tunnel_info *tun_info, BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) * 8)) - 1 > sizeof(key->tun_opts)); - memcpy(GENEVE_OPTS(key, tun_info->options_len), + memcpy(TUN_METADATA_OPTS(key, tun_info->options_len), tun_info->options, tun_info->options_len); key->tun_opts_len = tun_info->options_len; } else { diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index a8b30f334388..d3d0a406562d 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -53,7 +53,7 @@ struct ovs_key_ipv4_tunnel { struct ovs_tunnel_info { struct ovs_key_ipv4_tunnel tunnel; - const struct geneve_opt *options; + const void *options; u8 options_len; }; @@ -61,10 +61,10 @@ struct ovs_tunnel_info { * maximum size. This allows us to get the benefits of variable length * matching for small options. */ -#define GENEVE_OPTS(flow_key, opt_len) \ - ((struct geneve_opt *)((flow_key)->tun_opts + \ - FIELD_SIZEOF(struct sw_flow_key, tun_opts) - \ - opt_len)) +#define TUN_METADATA_OFFSET(opt_len) \ + (FIELD_SIZEOF(struct sw_flow_key, tun_opts) - opt_len) +#define TUN_METADATA_OPTS(flow_key, opt_len) \ + ((void *)((flow_key)->tun_opts + TUN_METADATA_OFFSET(opt_len))) static inline void __ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, __be32 saddr, __be32 daddr, @@ -73,7 +73,7 @@ static inline void __ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, __be16 tp_dst, __be64 tun_id, __be16 tun_flags, - const struct geneve_opt *opts, + const void *opts, u8 opts_len) { tun_info->tunnel.tun_id = tun_id; @@ -105,7 +105,7 @@ static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info, __be16 tp_dst, __be64 tun_id, __be16 tun_flags, - const struct geneve_opt *opts, + const void *opts, u8 opts_len) { __ovs_flow_tun_info_init(tun_info, iph->saddr, iph->daddr, diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 9645a21d9eaa..d210d1be3470 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -49,6 +49,14 @@ #include <net/mpls.h> #include "flow_netlink.h" +#include "vport-vxlan.h" + +struct ovs_len_tbl { + int len; + const struct ovs_len_tbl *next; +}; + +#define OVS_ATTR_NESTED -1 static void update_range(struct sw_flow_match *match, size_t offset, size_t size, bool is_mask) @@ -261,6 +269,9 @@ size_t ovs_tun_key_attr_size(void) + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_CSUM */ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_OAM */ + nla_total_size(256) /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */ + /* OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS is mutually exclusive with + * OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS and covered by it. + */ + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_SRC */ + nla_total_size(2); /* OVS_TUNNEL_KEY_ATTR_TP_DST */ } @@ -289,29 +300,45 @@ size_t ovs_key_attr_size(void) + nla_total_size(28); /* OVS_KEY_ATTR_ND */ } +static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = { + [OVS_TUNNEL_KEY_ATTR_ID] = { .len = sizeof(u64) }, + [OVS_TUNNEL_KEY_ATTR_IPV4_SRC] = { .len = sizeof(u32) }, + [OVS_TUNNEL_KEY_ATTR_IPV4_DST] = { .len = sizeof(u32) }, + [OVS_TUNNEL_KEY_ATTR_TOS] = { .len = 1 }, + [OVS_TUNNEL_KEY_ATTR_TTL] = { .len = 1 }, + [OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = { .len = 0 }, + [OVS_TUNNEL_KEY_ATTR_CSUM] = { .len = 0 }, + [OVS_TUNNEL_KEY_ATTR_TP_SRC] = { .len = sizeof(u16) }, + [OVS_TUNNEL_KEY_ATTR_TP_DST] = { .len = sizeof(u16) }, + [OVS_TUNNEL_KEY_ATTR_OAM] = { .len = 0 }, + [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_NESTED }, + [OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED }, +}; + /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ -static const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { - [OVS_KEY_ATTR_ENCAP] = -1, - [OVS_KEY_ATTR_PRIORITY] = sizeof(u32), - [OVS_KEY_ATTR_IN_PORT] = sizeof(u32), - [OVS_KEY_ATTR_SKB_MARK] = sizeof(u32), - [OVS_KEY_ATTR_ETHERNET] = sizeof(struct ovs_key_ethernet), - [OVS_KEY_ATTR_VLAN] = sizeof(__be16), - [OVS_KEY_ATTR_ETHERTYPE] = sizeof(__be16), - [OVS_KEY_ATTR_IPV4] = sizeof(struct ovs_key_ipv4), - [OVS_KEY_ATTR_IPV6] = sizeof(struct ovs_key_ipv6), - [OVS_KEY_ATTR_TCP] = sizeof(struct ovs_key_tcp), - [OVS_KEY_ATTR_TCP_FLAGS] = sizeof(__be16), - [OVS_KEY_ATTR_UDP] = sizeof(struct ovs_key_udp), - [OVS_KEY_ATTR_SCTP] = sizeof(struct ovs_key_sctp), - [OVS_KEY_ATTR_ICMP] = sizeof(struct ovs_key_icmp), - [OVS_KEY_ATTR_ICMPV6] = sizeof(struct ovs_key_icmpv6), - [OVS_KEY_ATTR_ARP] = sizeof(struct ovs_key_arp), - [OVS_KEY_ATTR_ND] = sizeof(struct ovs_key_nd), - [OVS_KEY_ATTR_RECIRC_ID] = sizeof(u32), - [OVS_KEY_ATTR_DP_HASH] = sizeof(u32), - [OVS_KEY_ATTR_TUNNEL] = -1, - [OVS_KEY_ATTR_MPLS] = sizeof(struct ovs_key_mpls), +static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { + [OVS_KEY_ATTR_ENCAP] = { .len = OVS_ATTR_NESTED }, + [OVS_KEY_ATTR_PRIORITY] = { .len = sizeof(u32) }, + [OVS_KEY_ATTR_IN_PORT] = { .len = sizeof(u32) }, + [OVS_KEY_ATTR_SKB_MARK] = { .len = sizeof(u32) }, + [OVS_KEY_ATTR_ETHERNET] = { .len = sizeof(struct ovs_key_ethernet) }, + [OVS_KEY_ATTR_VLAN] = { .len = sizeof(__be16) }, + [OVS_KEY_ATTR_ETHERTYPE] = { .len = sizeof(__be16) }, + [OVS_KEY_ATTR_IPV4] = { .len = sizeof(struct ovs_key_ipv4) }, + [OVS_KEY_ATTR_IPV6] = { .len = sizeof(struct ovs_key_ipv6) }, + [OVS_KEY_ATTR_TCP] = { .len = sizeof(struct ovs_key_tcp) }, + [OVS_KEY_ATTR_TCP_FLAGS] = { .len = sizeof(__be16) }, + [OVS_KEY_ATTR_UDP] = { .len = sizeof(struct ovs_key_udp) }, + [OVS_KEY_ATTR_SCTP] = { .len = sizeof(struct ovs_key_sctp) }, + [OVS_KEY_ATTR_ICMP] = { .len = sizeof(struct ovs_key_icmp) }, + [OVS_KEY_ATTR_ICMPV6] = { .len = sizeof(struct ovs_key_icmpv6) }, + [OVS_KEY_ATTR_ARP] = { .len = sizeof(struct ovs_key_arp) }, + [OVS_KEY_ATTR_ND] = { .len = sizeof(struct ovs_key_nd) }, + [OVS_KEY_ATTR_RECIRC_ID] = { .len = sizeof(u32) }, + [OVS_KEY_ATTR_DP_HASH] = { .len = sizeof(u32) }, + [OVS_KEY_ATTR_TUNNEL] = { .len = OVS_ATTR_NESTED, + .next = ovs_tunnel_key_lens, }, + [OVS_KEY_ATTR_MPLS] = { .len = sizeof(struct ovs_key_mpls) }, }; static bool is_all_zero(const u8 *fp, size_t size) @@ -352,8 +379,8 @@ static int __parse_flow_nlattrs(const struct nlattr *attr, return -EINVAL; } - expected_len = ovs_key_lens[type]; - if (nla_len(nla) != expected_len && expected_len != -1) { + expected_len = ovs_key_lens[type].len; + if (nla_len(nla) != expected_len && expected_len != OVS_ATTR_NESTED) { OVS_NLERR(log, "Key %d has unexpected len %d expected %d", type, nla_len(nla), expected_len); return -EINVAL; @@ -432,13 +459,47 @@ static int genev_tun_opt_from_nlattr(const struct nlattr *a, SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, true); } - opt_key_offset = (unsigned long)GENEVE_OPTS((struct sw_flow_key *)0, - nla_len(a)); + opt_key_offset = TUN_METADATA_OFFSET(nla_len(a)); SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, nla_data(a), nla_len(a), is_mask); return 0; } +static const struct nla_policy vxlan_opt_policy[OVS_VXLAN_EXT_MAX + 1] = { + [OVS_VXLAN_EXT_GBP] = { .type = NLA_U32 }, +}; + +static int vxlan_tun_opt_from_nlattr(const struct nlattr *a, + struct sw_flow_match *match, bool is_mask, + bool log) +{ + struct nlattr *tb[OVS_VXLAN_EXT_MAX+1]; + unsigned long opt_key_offset; + struct ovs_vxlan_opts opts; + int err; + + BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts)); + + err = nla_parse_nested(tb, OVS_VXLAN_EXT_MAX, a, vxlan_opt_policy); + if (err < 0) + return err; + + memset(&opts, 0, sizeof(opts)); + + if (tb[OVS_VXLAN_EXT_GBP]) + opts.gbp = nla_get_u32(tb[OVS_VXLAN_EXT_GBP]); + + if (!is_mask) + SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), false); + else + SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, true); + + opt_key_offset = TUN_METADATA_OFFSET(sizeof(opts)); + SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, &opts, sizeof(opts), + is_mask); + return 0; +} + static int ipv4_tun_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool log) @@ -447,35 +508,22 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, int rem; bool ttl = false; __be16 tun_flags = 0; + int opts_type = 0; nla_for_each_nested(a, attr, rem) { int type = nla_type(a); int err; - static const u32 ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = { - [OVS_TUNNEL_KEY_ATTR_ID] = sizeof(u64), - [OVS_TUNNEL_KEY_ATTR_IPV4_SRC] = sizeof(u32), - [OVS_TUNNEL_KEY_ATTR_IPV4_DST] = sizeof(u32), - [OVS_TUNNEL_KEY_ATTR_TOS] = 1, - [OVS_TUNNEL_KEY_ATTR_TTL] = 1, - [OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = 0, - [OVS_TUNNEL_KEY_ATTR_CSUM] = 0, - [OVS_TUNNEL_KEY_ATTR_TP_SRC] = sizeof(u16), - [OVS_TUNNEL_KEY_ATTR_TP_DST] = sizeof(u16), - [OVS_TUNNEL_KEY_ATTR_OAM] = 0, - [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = -1, - }; - if (type > OVS_TUNNEL_KEY_ATTR_MAX) { OVS_NLERR(log, "Tunnel attr %d out of range max %d", type, OVS_TUNNEL_KEY_ATTR_MAX); return -EINVAL; } - if (ovs_tunnel_key_lens[type] != nla_len(a) && - ovs_tunnel_key_lens[type] != -1) { + if (ovs_tunnel_key_lens[type].len != nla_len(a) && + ovs_tunnel_key_lens[type].len != OVS_ATTR_NESTED) { OVS_NLERR(log, "Tunnel attr %d has unexpected len %d expected %d", - type, nla_len(a), ovs_tunnel_key_lens[type]); + type, nla_len(a), ovs_tunnel_key_lens[type].len); return -EINVAL; } @@ -520,11 +568,30 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, tun_flags |= TUNNEL_OAM; break; case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS: + if (opts_type) { + OVS_NLERR(log, "Multiple metadata blocks provided"); + return -EINVAL; + } + err = genev_tun_opt_from_nlattr(a, match, is_mask, log); if (err) return err; - tun_flags |= TUNNEL_OPTIONS_PRESENT; + tun_flags |= TUNNEL_GENEVE_OPT; + opts_type = type; + break; + case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: + if (opts_type) { + OVS_NLERR(log, "Multiple metadata blocks provided"); + return -EINVAL; + } + + err = vxlan_tun_opt_from_nlattr(a, match, is_mask, log); + if (err) + return err; + + tun_flags |= TUNNEL_VXLAN_OPT; + opts_type = type; break; default: OVS_NLERR(log, "Unknown IPv4 tunnel attribute %d", @@ -553,13 +620,29 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, } } + return opts_type; +} + +static int vxlan_opt_to_nlattr(struct sk_buff *skb, + const void *tun_opts, int swkey_tun_opts_len) +{ + const struct ovs_vxlan_opts *opts = tun_opts; + struct nlattr *nla; + + nla = nla_nest_start(skb, OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS); + if (!nla) + return -EMSGSIZE; + + if (nla_put_u32(skb, OVS_VXLAN_EXT_GBP, opts->gbp) < 0) + return -EMSGSIZE; + + nla_nest_end(skb, nla); return 0; } static int __ipv4_tun_to_nlattr(struct sk_buff *skb, const struct ovs_key_ipv4_tunnel *output, - const struct geneve_opt *tun_opts, - int swkey_tun_opts_len) + const void *tun_opts, int swkey_tun_opts_len) { if (output->tun_flags & TUNNEL_KEY && nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id)) @@ -590,18 +673,22 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb, if ((output->tun_flags & TUNNEL_OAM) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM)) return -EMSGSIZE; - if (tun_opts && - nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, - swkey_tun_opts_len, tun_opts)) - return -EMSGSIZE; + if (tun_opts) { + if (output->tun_flags & TUNNEL_GENEVE_OPT && + nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, + swkey_tun_opts_len, tun_opts)) + return -EMSGSIZE; + else if (output->tun_flags & TUNNEL_VXLAN_OPT && + vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len)) + return -EMSGSIZE; + } return 0; } static int ipv4_tun_to_nlattr(struct sk_buff *skb, const struct ovs_key_ipv4_tunnel *output, - const struct geneve_opt *tun_opts, - int swkey_tun_opts_len) + const void *tun_opts, int swkey_tun_opts_len) { struct nlattr *nla; int err; @@ -675,7 +762,7 @@ static int metadata_from_nlattrs(struct sw_flow_match *match, u64 *attrs, } if (*attrs & (1 << OVS_KEY_ATTR_TUNNEL)) { if (ipv4_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match, - is_mask, log)) + is_mask, log) < 0) return -EINVAL; *attrs &= ~(1 << OVS_KEY_ATTR_TUNNEL); } @@ -915,18 +1002,16 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, return 0; } -static void nlattr_set(struct nlattr *attr, u8 val, bool is_attr_mask_key) +static void nlattr_set(struct nlattr *attr, u8 val, + const struct ovs_len_tbl *tbl) { struct nlattr *nla; int rem; /* The nlattr stream should already have been validated */ nla_for_each_nested(nla, attr, rem) { - /* We assume that ovs_key_lens[type] == -1 means that type is a - * nested attribute - */ - if (is_attr_mask_key && ovs_key_lens[nla_type(nla)] == -1) - nlattr_set(nla, val, false); + if (tbl && tbl[nla_type(nla)].len == OVS_ATTR_NESTED) + nlattr_set(nla, val, tbl[nla_type(nla)].next); else memset(nla_data(nla), val, nla_len(nla)); } @@ -934,7 +1019,7 @@ static void nlattr_set(struct nlattr *attr, u8 val, bool is_attr_mask_key) static void mask_set_nlattr(struct nlattr *attr, u8 val) { - nlattr_set(attr, val, true); + nlattr_set(attr, val, ovs_key_lens); } /** @@ -1148,10 +1233,10 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, goto nla_put_failure; if ((swkey->tun_key.ipv4_dst || is_mask)) { - const struct geneve_opt *opts = NULL; + const void *opts = NULL; if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT) - opts = GENEVE_OPTS(output, swkey->tun_opts_len); + opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len); if (ipv4_tun_to_nlattr(skb, &output->tun_key, opts, swkey->tun_opts_len)) @@ -1540,6 +1625,34 @@ void ovs_match_init(struct sw_flow_match *match, } } +static int validate_geneve_opts(struct sw_flow_key *key) +{ + struct geneve_opt *option; + int opts_len = key->tun_opts_len; + bool crit_opt = false; + + option = (struct geneve_opt *)TUN_METADATA_OPTS(key, key->tun_opts_len); + while (opts_len > 0) { + int len; + + if (opts_len < sizeof(*option)) + return -EINVAL; + + len = sizeof(*option) + option->length * 4; + if (len > opts_len) + return -EINVAL; + + crit_opt |= !!(option->type & GENEVE_CRIT_OPT_TYPE); + + option = (struct geneve_opt *)((u8 *)option + len); + opts_len -= len; + }; + + key->tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0; + + return 0; +} + static int validate_and_copy_set_tun(const struct nlattr *attr, struct sw_flow_actions **sfa, bool log) { @@ -1547,36 +1660,23 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, struct sw_flow_key key; struct ovs_tunnel_info *tun_info; struct nlattr *a; - int err, start; + int err, start, opts_type; ovs_match_init(&match, &key, NULL); - err = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log); - if (err) - return err; + opts_type = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log); + if (opts_type < 0) + return opts_type; if (key.tun_opts_len) { - struct geneve_opt *option = GENEVE_OPTS(&key, - key.tun_opts_len); - int opts_len = key.tun_opts_len; - bool crit_opt = false; - - while (opts_len > 0) { - int len; - - if (opts_len < sizeof(*option)) - return -EINVAL; - - len = sizeof(*option) + option->length * 4; - if (len > opts_len) - return -EINVAL; - - crit_opt |= !!(option->type & GENEVE_CRIT_OPT_TYPE); - - option = (struct geneve_opt *)((u8 *)option + len); - opts_len -= len; - }; - - key.tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0; + switch (opts_type) { + case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS: + err = validate_geneve_opts(&key); + if (err < 0) + return err; + break; + case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: + break; + } }; start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET, log); @@ -1597,9 +1697,9 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, * everything else will go away after flow setup. We can append * it to tun_info and then point there. */ - memcpy((tun_info + 1), GENEVE_OPTS(&key, key.tun_opts_len), - key.tun_opts_len); - tun_info->options = (struct geneve_opt *)(tun_info + 1); + memcpy((tun_info + 1), + TUN_METADATA_OPTS(&key, key.tun_opts_len), key.tun_opts_len); + tun_info->options = (tun_info + 1); } else { tun_info->options = NULL; } @@ -1622,8 +1722,8 @@ static int validate_set(const struct nlattr *a, return -EINVAL; if (key_type > OVS_KEY_ATTR_MAX || - (ovs_key_lens[key_type] != nla_len(ovs_key) && - ovs_key_lens[key_type] != -1)) + (ovs_key_lens[key_type].len != nla_len(ovs_key) && + ovs_key_lens[key_type].len != OVS_ATTR_NESTED)) return -EINVAL; switch (key_type) { @@ -1753,7 +1853,6 @@ static int __ovs_nla_copy_actions(const struct nlattr *attr, __be16 eth_type, __be16 vlan_tci, bool log) { const struct nlattr *a; - bool out_tnl_port = false; int rem, err; if (depth >= SAMPLE_ACTION_DEPTH) @@ -1796,8 +1895,6 @@ static int __ovs_nla_copy_actions(const struct nlattr *attr, case OVS_ACTION_ATTR_OUTPUT: if (nla_get_u32(a) >= DP_MAX_PORTS) return -EINVAL; - out_tnl_port = false; - break; case OVS_ACTION_ATTR_HASH: { @@ -1832,12 +1929,6 @@ static int __ovs_nla_copy_actions(const struct nlattr *attr, case OVS_ACTION_ATTR_PUSH_MPLS: { const struct ovs_action_push_mpls *mpls = nla_data(a); - /* Networking stack do not allow simultaneous Tunnel - * and MPLS GSO. - */ - if (out_tnl_port) - return -EINVAL; - if (!eth_p_mpls(mpls->mpls_ethertype)) return -EINVAL; /* Prohibit push MPLS other than to a white list @@ -1873,11 +1964,9 @@ static int __ovs_nla_copy_actions(const struct nlattr *attr, case OVS_ACTION_ATTR_SET: err = validate_set(a, key, sfa, - &out_tnl_port, eth_type, log); + &skip_copy, eth_type, log); if (err) return err; - - skip_copy = out_tnl_port; break; case OVS_ACTION_ATTR_SAMPLE: diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 347fa2325b22..7ca3d454ff3b 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -9,8 +9,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/version.h> - #include <linux/in.h> #include <linux/ip.h> #include <linux/net.h> @@ -90,7 +88,7 @@ static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb) opts_len = geneveh->opt_len * 4; - flags = TUNNEL_KEY | TUNNEL_OPTIONS_PRESENT | + flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT | (udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0) | (geneveh->oam ? TUNNEL_OAM : 0) | (geneveh->critical ? TUNNEL_CRIT_OPT : 0); @@ -172,7 +170,7 @@ error: static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb) { - struct ovs_key_ipv4_tunnel *tun_key; + const struct ovs_key_ipv4_tunnel *tun_key; struct ovs_tunnel_info *tun_info; struct net *net = ovs_dp_get_net(vport->dp); struct geneve_port *geneve_port = geneve_vport(vport); @@ -180,7 +178,7 @@ static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb) __be16 sport; struct rtable *rt; struct flowi4 fl; - u8 vni[3]; + u8 vni[3], opts_len, *opts; __be16 df; int err; @@ -191,16 +189,7 @@ static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb) } tun_key = &tun_info->tunnel; - - /* Route lookup */ - memset(&fl, 0, sizeof(fl)); - fl.daddr = tun_key->ipv4_dst; - fl.saddr = tun_key->ipv4_src; - fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos); - fl.flowi4_mark = skb->mark; - fl.flowi4_proto = IPPROTO_UDP; - - rt = ip_route_output_key(net, &fl); + rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP); if (IS_ERR(rt)) { err = PTR_ERR(rt); goto error; @@ -211,15 +200,25 @@ static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb) tunnel_id_to_vni(tun_key->tun_id, vni); skb->ignore_df = 1; + if (tun_key->tun_flags & TUNNEL_GENEVE_OPT) { + opts = (u8 *)tun_info->options; + opts_len = tun_info->options_len; + } else { + opts = NULL; + opts_len = 0; + } + err = geneve_xmit_skb(geneve_port->gs, rt, skb, fl.saddr, tun_key->ipv4_dst, tun_key->ipv4_tos, tun_key->ipv4_ttl, df, sport, dport, - tun_key->tun_flags, vni, - tun_info->options_len, (u8 *)tun_info->options, + tun_key->tun_flags, vni, opts_len, opts, false); if (err < 0) ip_rt_put(rt); + return err; + error: + kfree_skb(skb); return err; } diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index 6b69df545b1d..f17ac9642f4e 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -73,7 +73,7 @@ static struct sk_buff *__build_header(struct sk_buff *skb, skb = gre_handle_offloads(skb, !!(tun_key->tun_flags & TUNNEL_CSUM)); if (IS_ERR(skb)) - return NULL; + return skb; tpi.flags = filter_tnl_flags(tun_key->tun_flags); tpi.proto = htons(ETH_P_TEB); @@ -134,7 +134,7 @@ static int gre_err(struct sk_buff *skb, u32 info, static int gre_tnl_send(struct vport *vport, struct sk_buff *skb) { struct net *net = ovs_dp_get_net(vport->dp); - struct ovs_key_ipv4_tunnel *tun_key; + const struct ovs_key_ipv4_tunnel *tun_key; struct flowi4 fl; struct rtable *rt; int min_headroom; @@ -144,27 +144,21 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb) if (unlikely(!OVS_CB(skb)->egress_tun_info)) { err = -EINVAL; - goto error; + goto err_free_skb; } tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; - /* Route lookup */ - memset(&fl, 0, sizeof(fl)); - fl.daddr = tun_key->ipv4_dst; - fl.saddr = tun_key->ipv4_src; - fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos); - fl.flowi4_mark = skb->mark; - fl.flowi4_proto = IPPROTO_GRE; - - rt = ip_route_output_key(net, &fl); - if (IS_ERR(rt)) - return PTR_ERR(rt); + rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_GRE); + if (IS_ERR(rt)) { + err = PTR_ERR(rt); + goto err_free_skb; + } tunnel_hlen = ip_gre_calc_hlen(tun_key->tun_flags); min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len + tunnel_hlen + sizeof(struct iphdr) - + (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0); + + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) { int head_delta = SKB_DATA_ALIGN(min_headroom - skb_headroom(skb) + @@ -183,8 +177,9 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb) /* Push Tunnel header. */ skb = __build_header(skb, tunnel_hlen); - if (unlikely(!skb)) { - err = 0; + if (IS_ERR(skb)) { + err = PTR_ERR(skb); + skb = NULL; goto err_free_rt; } @@ -198,7 +193,8 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb) tun_key->ipv4_tos, tun_key->ipv4_ttl, df, false); err_free_rt: ip_rt_put(rt); -error: +err_free_skb: + kfree_skb(skb); return err; } diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 38f95a52241b..8a2d54cba9ba 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -40,6 +40,7 @@ #include "datapath.h" #include "vport.h" +#include "vport-vxlan.h" /** * struct vxlan_port - Keeps track of open UDP ports @@ -49,6 +50,7 @@ struct vxlan_port { struct vxlan_sock *vs; char name[IFNAMSIZ]; + u32 exts; /* VXLAN_F_* in <net/vxlan.h> */ }; static struct vport_ops ovs_vxlan_vport_ops; @@ -59,19 +61,30 @@ static inline struct vxlan_port *vxlan_vport(const struct vport *vport) } /* Called with rcu_read_lock and BH disabled. */ -static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni) +static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, + struct vxlan_metadata *md) { struct ovs_tunnel_info tun_info; + struct vxlan_port *vxlan_port; struct vport *vport = vs->data; struct iphdr *iph; + struct ovs_vxlan_opts opts = { + .gbp = md->gbp, + }; __be64 key; + __be16 flags; + + flags = TUNNEL_KEY; + vxlan_port = vxlan_vport(vport); + if (vxlan_port->exts & VXLAN_F_GBP) + flags |= TUNNEL_VXLAN_OPT; /* Save outer tunnel values */ iph = ip_hdr(skb); - key = cpu_to_be64(ntohl(vx_vni) >> 8); + key = cpu_to_be64(ntohl(md->vni) >> 8); ovs_flow_tun_info_init(&tun_info, iph, udp_hdr(skb)->source, udp_hdr(skb)->dest, - key, TUNNEL_KEY, NULL, 0); + key, flags, &opts, sizeof(opts)); ovs_vport_receive(vport, skb, &tun_info); } @@ -83,6 +96,21 @@ static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb) if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port))) return -EMSGSIZE; + + if (vxlan_port->exts) { + struct nlattr *exts; + + exts = nla_nest_start(skb, OVS_TUNNEL_ATTR_EXTENSION); + if (!exts) + return -EMSGSIZE; + + if (vxlan_port->exts & VXLAN_F_GBP && + nla_put_flag(skb, OVS_VXLAN_EXT_GBP)) + return -EMSGSIZE; + + nla_nest_end(skb, exts); + } + return 0; } @@ -95,6 +123,31 @@ static void vxlan_tnl_destroy(struct vport *vport) ovs_vport_deferred_free(vport); } +static const struct nla_policy exts_policy[OVS_VXLAN_EXT_MAX+1] = { + [OVS_VXLAN_EXT_GBP] = { .type = NLA_FLAG, }, +}; + +static int vxlan_configure_exts(struct vport *vport, struct nlattr *attr) +{ + struct nlattr *exts[OVS_VXLAN_EXT_MAX+1]; + struct vxlan_port *vxlan_port; + int err; + + if (nla_len(attr) < sizeof(struct nlattr)) + return -EINVAL; + + err = nla_parse_nested(exts, OVS_VXLAN_EXT_MAX, attr, exts_policy); + if (err < 0) + return err; + + vxlan_port = vxlan_vport(vport); + + if (exts[OVS_VXLAN_EXT_GBP]) + vxlan_port->exts |= VXLAN_F_GBP; + + return 0; +} + static struct vport *vxlan_tnl_create(const struct vport_parms *parms) { struct net *net = ovs_dp_get_net(parms->dp); @@ -127,7 +180,17 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) vxlan_port = vxlan_vport(vport); strncpy(vxlan_port->name, parms->name, IFNAMSIZ); - vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, 0); + a = nla_find_nested(options, OVS_TUNNEL_ATTR_EXTENSION); + if (a) { + err = vxlan_configure_exts(vport, a); + if (err) { + ovs_vport_free(vport); + goto error; + } + } + + vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, + vxlan_port->exts); if (IS_ERR(vs)) { ovs_vport_free(vport); return (void *)vs; @@ -140,12 +203,28 @@ error: return ERR_PTR(err); } +static int vxlan_ext_gbp(struct sk_buff *skb) +{ + const struct ovs_tunnel_info *tun_info; + const struct ovs_vxlan_opts *opts; + + tun_info = OVS_CB(skb)->egress_tun_info; + opts = tun_info->options; + + if (tun_info->tunnel.tun_flags & TUNNEL_VXLAN_OPT && + tun_info->options_len >= sizeof(*opts)) + return opts->gbp; + else + return 0; +} + static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb) { struct net *net = ovs_dp_get_net(vport->dp); struct vxlan_port *vxlan_port = vxlan_vport(vport); __be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport; - struct ovs_key_ipv4_tunnel *tun_key; + const struct ovs_key_ipv4_tunnel *tun_key; + struct vxlan_metadata md = {0}; struct rtable *rt; struct flowi4 fl; __be16 src_port; @@ -158,15 +237,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb) } tun_key = &OVS_CB(skb)->egress_tun_info->tunnel; - /* Route lookup */ - memset(&fl, 0, sizeof(fl)); - fl.daddr = tun_key->ipv4_dst; - fl.saddr = tun_key->ipv4_src; - fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos); - fl.flowi4_mark = skb->mark; - fl.flowi4_proto = IPPROTO_UDP; - - rt = ip_route_output_key(net, &fl); + rt = ovs_tunnel_route_lookup(net, tun_key, skb->mark, &fl, IPPROTO_UDP); if (IS_ERR(rt)) { err = PTR_ERR(rt); goto error; @@ -178,16 +249,20 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb) skb->ignore_df = 1; src_port = udp_flow_src_port(net, skb, 0, 0, true); + md.vni = htonl(be64_to_cpu(tun_key->tun_id) << 8); + md.gbp = vxlan_ext_gbp(skb); err = vxlan_xmit_skb(vxlan_port->vs, rt, skb, fl.saddr, tun_key->ipv4_dst, tun_key->ipv4_tos, tun_key->ipv4_ttl, df, src_port, dst_port, - htonl(be64_to_cpu(tun_key->tun_id) << 8), + &md, false); if (err < 0) ip_rt_put(rt); + return err; error: + kfree_skb(skb); return err; } diff --git a/net/openvswitch/vport-vxlan.h b/net/openvswitch/vport-vxlan.h new file mode 100644 index 000000000000..4b08233e73d5 --- /dev/null +++ b/net/openvswitch/vport-vxlan.h @@ -0,0 +1,11 @@ +#ifndef VPORT_VXLAN_H +#define VPORT_VXLAN_H 1 + +#include <linux/kernel.h> +#include <linux/types.h> + +struct ovs_vxlan_opts { + __u32 gbp; +}; + +#endif diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 9584526c0778..ec2954ffc690 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -480,7 +480,8 @@ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb, stats = this_cpu_ptr(vport->percpu_stats); u64_stats_update_begin(&stats->syncp); stats->rx_packets++; - stats->rx_bytes += skb->len; + stats->rx_bytes += skb->len + + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); u64_stats_update_end(&stats->syncp); OVS_CB(skb)->input_vport = vport; @@ -519,10 +520,9 @@ int ovs_vport_send(struct vport *vport, struct sk_buff *skb) u64_stats_update_end(&stats->syncp); } else if (sent < 0) { ovs_vport_record_error(vport, VPORT_E_TX_ERROR); - kfree_skb(skb); - } else + } else { ovs_vport_record_error(vport, VPORT_E_TX_DROPPED); - + } return sent; } @@ -595,14 +595,7 @@ int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info, * The process may need to be changed if the corresponding process * in vports ops changed. */ - memset(&fl, 0, sizeof(fl)); - fl.daddr = tun_key->ipv4_dst; - fl.saddr = tun_key->ipv4_src; - fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos); - fl.flowi4_mark = skb_mark; - fl.flowi4_proto = ipproto; - - rt = ip_route_output_key(net, &fl); + rt = ovs_tunnel_route_lookup(net, tun_key, skb_mark, &fl, ipproto); if (IS_ERR(rt)) return PTR_ERR(rt); diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index 99c8e71d9e6c..f8ae295fb001 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -236,4 +236,22 @@ static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb, int ovs_vport_ops_register(struct vport_ops *ops); void ovs_vport_ops_unregister(struct vport_ops *ops); +static inline struct rtable *ovs_tunnel_route_lookup(struct net *net, + const struct ovs_key_ipv4_tunnel *key, + u32 mark, + struct flowi4 *fl, + u8 protocol) +{ + struct rtable *rt; + + memset(fl, 0, sizeof(*fl)); + fl->daddr = key->ipv4_dst; + fl->saddr = key->ipv4_src; + fl->flowi4_tos = RT_TOS(key->ipv4_tos); + fl->flowi4_mark = mark; + fl->flowi4_proto = protocol; + + rt = ip_route_output_key(net, fl); + return rt; +} #endif /* vport.h */ |