diff options
Diffstat (limited to 'net/openvswitch/actions.c')
-rw-r--r-- | net/openvswitch/actions.c | 355 |
1 files changed, 223 insertions, 132 deletions
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 8c4229b11c34..764fdc39c63b 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -28,10 +28,12 @@ #include <linux/in6.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> + #include <net/ip.h> #include <net/ipv6.h> #include <net/checksum.h> #include <net/dsfield.h> +#include <net/mpls.h> #include <net/sctp/checksum.h> #include "datapath.h" @@ -67,7 +69,7 @@ static void action_fifo_init(struct action_fifo *fifo) fifo->tail = 0; } -static bool action_fifo_is_empty(struct action_fifo *fifo) +static bool action_fifo_is_empty(const struct action_fifo *fifo) { return (fifo->head == fifo->tail); } @@ -90,7 +92,7 @@ static struct deferred_action *action_fifo_put(struct action_fifo *fifo) /* Return true if fifo is not full */ static struct deferred_action *add_deferred_actions(struct sk_buff *skb, - struct sw_flow_key *key, + const struct sw_flow_key *key, const struct nlattr *attr) { struct action_fifo *fifo; @@ -107,100 +109,131 @@ static struct deferred_action *add_deferred_actions(struct sk_buff *skb, return da; } -static int make_writable(struct sk_buff *skb, int write_len) +static void invalidate_flow_key(struct sw_flow_key *key) +{ + key->eth.type = htons(0); +} + +static bool is_flow_key_valid(const struct sw_flow_key *key) { - if (!pskb_may_pull(skb, write_len)) + return !!key->eth.type; +} + +static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key, + const struct ovs_action_push_mpls *mpls) +{ + __be32 *new_mpls_lse; + struct ethhdr *hdr; + + /* Networking stack do not allow simultaneous Tunnel and MPLS GSO. */ + if (skb->encapsulation) + return -ENOTSUPP; + + if (skb_cow_head(skb, MPLS_HLEN) < 0) return -ENOMEM; - if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) - return 0; + skb_push(skb, MPLS_HLEN); + memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb), + skb->mac_len); + skb_reset_mac_header(skb); + + new_mpls_lse = (__be32 *)skb_mpls_header(skb); + *new_mpls_lse = mpls->mpls_lse; - return pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_add(skb->csum, csum_partial(new_mpls_lse, + MPLS_HLEN, 0)); + + hdr = eth_hdr(skb); + hdr->h_proto = mpls->mpls_ethertype; + + skb_set_inner_protocol(skb, skb->protocol); + skb->protocol = mpls->mpls_ethertype; + + invalidate_flow_key(key); + return 0; } -/* remove VLAN header from packet and update csum accordingly. */ -static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci) +static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key, + const __be16 ethertype) { - struct vlan_hdr *vhdr; + struct ethhdr *hdr; int err; - err = make_writable(skb, VLAN_ETH_HLEN); + err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN); if (unlikely(err)) return err; - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->csum = csum_sub(skb->csum, csum_partial(skb->data - + (2 * ETH_ALEN), VLAN_HLEN, 0)); + skb_postpull_rcsum(skb, skb_mpls_header(skb), MPLS_HLEN); - vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN); - *current_tci = vhdr->h_vlan_TCI; + memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb), + skb->mac_len); - memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN); - __skb_pull(skb, VLAN_HLEN); + __skb_pull(skb, MPLS_HLEN); + skb_reset_mac_header(skb); - vlan_set_encap_proto(skb, vhdr); - skb->mac_header += VLAN_HLEN; - if (skb_network_offset(skb) < ETH_HLEN) - skb_set_network_header(skb, ETH_HLEN); - skb_reset_mac_len(skb); + /* skb_mpls_header() is used to locate the ethertype + * field correctly in the presence of VLAN tags. + */ + hdr = (struct ethhdr *)(skb_mpls_header(skb) - ETH_HLEN); + hdr->h_proto = ethertype; + if (eth_p_mpls(skb->protocol)) + skb->protocol = ethertype; + invalidate_flow_key(key); return 0; } -static int pop_vlan(struct sk_buff *skb) +static int set_mpls(struct sk_buff *skb, struct sw_flow_key *key, + const __be32 *mpls_lse) { - __be16 tci; + __be32 *stack; int err; - if (likely(vlan_tx_tag_present(skb))) { - skb->vlan_tci = 0; - } else { - if (unlikely(skb->protocol != htons(ETH_P_8021Q) || - skb->len < VLAN_ETH_HLEN)) - return 0; - - err = __pop_vlan_tci(skb, &tci); - if (err) - return err; - } - /* move next vlan tag to hw accel tag */ - if (likely(skb->protocol != htons(ETH_P_8021Q) || - skb->len < VLAN_ETH_HLEN)) - return 0; - - err = __pop_vlan_tci(skb, &tci); + err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN); if (unlikely(err)) return err; - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), ntohs(tci)); + stack = (__be32 *)skb_mpls_header(skb); + if (skb->ip_summed == CHECKSUM_COMPLETE) { + __be32 diff[] = { ~(*stack), *mpls_lse }; + skb->csum = ~csum_partial((char *)diff, sizeof(diff), + ~skb->csum); + } + + *stack = *mpls_lse; + key->mpls.top_lse = *mpls_lse; return 0; } -static int push_vlan(struct sk_buff *skb, const struct ovs_action_push_vlan *vlan) +static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key) { - if (unlikely(vlan_tx_tag_present(skb))) { - u16 current_tag; - - /* push down current VLAN tag */ - current_tag = vlan_tx_tag_get(skb); - - if (!__vlan_put_tag(skb, skb->vlan_proto, current_tag)) - return -ENOMEM; + int err; - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->csum = csum_add(skb->csum, csum_partial(skb->data - + (2 * ETH_ALEN), VLAN_HLEN, 0)); + err = skb_vlan_pop(skb); + if (vlan_tx_tag_present(skb)) + invalidate_flow_key(key); + else + key->eth.tci = 0; + return err; +} - } - __vlan_hwaccel_put_tag(skb, vlan->vlan_tpid, ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT); - return 0; +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)) + invalidate_flow_key(key); + else + key->eth.tci = vlan->vlan_tci; + return skb_vlan_push(skb, vlan->vlan_tpid, + ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT); } -static int set_eth_addr(struct sk_buff *skb, +static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *key, const struct ovs_key_ethernet *eth_key) { int err; - err = make_writable(skb, ETH_HLEN); + err = skb_ensure_writable(skb, ETH_HLEN); if (unlikely(err)) return err; @@ -211,11 +244,13 @@ static int set_eth_addr(struct sk_buff *skb, ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2); + ether_addr_copy(key->eth.src, eth_key->eth_src); + ether_addr_copy(key->eth.dst, eth_key->eth_dst); return 0; } static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh, - __be32 *addr, __be32 new_addr) + __be32 *addr, __be32 new_addr) { int transport_len = skb->len - skb_transport_offset(skb); @@ -298,42 +333,52 @@ static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl) nh->ttl = new_ttl; } -static int set_ipv4(struct sk_buff *skb, const struct ovs_key_ipv4 *ipv4_key) +static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *key, + const struct ovs_key_ipv4 *ipv4_key) { struct iphdr *nh; int err; - err = make_writable(skb, skb_network_offset(skb) + - sizeof(struct iphdr)); + err = skb_ensure_writable(skb, skb_network_offset(skb) + + sizeof(struct iphdr)); if (unlikely(err)) return err; nh = ip_hdr(skb); - if (ipv4_key->ipv4_src != nh->saddr) + if (ipv4_key->ipv4_src != nh->saddr) { set_ip_addr(skb, nh, &nh->saddr, ipv4_key->ipv4_src); + key->ipv4.addr.src = ipv4_key->ipv4_src; + } - if (ipv4_key->ipv4_dst != nh->daddr) + if (ipv4_key->ipv4_dst != nh->daddr) { set_ip_addr(skb, nh, &nh->daddr, ipv4_key->ipv4_dst); + key->ipv4.addr.dst = ipv4_key->ipv4_dst; + } - if (ipv4_key->ipv4_tos != nh->tos) + if (ipv4_key->ipv4_tos != nh->tos) { ipv4_change_dsfield(nh, 0, ipv4_key->ipv4_tos); + key->ip.tos = nh->tos; + } - if (ipv4_key->ipv4_ttl != nh->ttl) + if (ipv4_key->ipv4_ttl != nh->ttl) { set_ip_ttl(skb, nh, ipv4_key->ipv4_ttl); + key->ip.ttl = ipv4_key->ipv4_ttl; + } return 0; } -static int set_ipv6(struct sk_buff *skb, const struct ovs_key_ipv6 *ipv6_key) +static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *key, + const struct ovs_key_ipv6 *ipv6_key) { struct ipv6hdr *nh; int err; __be32 *saddr; __be32 *daddr; - err = make_writable(skb, skb_network_offset(skb) + - sizeof(struct ipv6hdr)); + err = skb_ensure_writable(skb, skb_network_offset(skb) + + sizeof(struct ipv6hdr)); if (unlikely(err)) return err; @@ -341,9 +386,12 @@ static int set_ipv6(struct sk_buff *skb, const struct ovs_key_ipv6 *ipv6_key) saddr = (__be32 *)&nh->saddr; daddr = (__be32 *)&nh->daddr; - if (memcmp(ipv6_key->ipv6_src, saddr, sizeof(ipv6_key->ipv6_src))) + if (memcmp(ipv6_key->ipv6_src, saddr, sizeof(ipv6_key->ipv6_src))) { set_ipv6_addr(skb, ipv6_key->ipv6_proto, saddr, ipv6_key->ipv6_src, true); + memcpy(&key->ipv6.addr.src, ipv6_key->ipv6_src, + sizeof(ipv6_key->ipv6_src)); + } if (memcmp(ipv6_key->ipv6_dst, daddr, sizeof(ipv6_key->ipv6_dst))) { unsigned int offset = 0; @@ -357,16 +405,22 @@ static int set_ipv6(struct sk_buff *skb, const struct ovs_key_ipv6 *ipv6_key) set_ipv6_addr(skb, ipv6_key->ipv6_proto, daddr, ipv6_key->ipv6_dst, recalc_csum); + memcpy(&key->ipv6.addr.dst, ipv6_key->ipv6_dst, + sizeof(ipv6_key->ipv6_dst)); } set_ipv6_tc(nh, ipv6_key->ipv6_tclass); + key->ip.tos = ipv6_get_dsfield(nh); + set_ipv6_fl(nh, ntohl(ipv6_key->ipv6_label)); - nh->hop_limit = ipv6_key->ipv6_hlimit; + key->ipv6.label = *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL); + nh->hop_limit = ipv6_key->ipv6_hlimit; + key->ip.ttl = ipv6_key->ipv6_hlimit; return 0; } -/* Must follow make_writable() since that can move the skb data. */ +/* 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) { @@ -390,54 +444,64 @@ static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port) } } -static int set_udp(struct sk_buff *skb, const struct ovs_key_udp *udp_port_key) +static int set_udp(struct sk_buff *skb, struct sw_flow_key *key, + const struct ovs_key_udp *udp_port_key) { struct udphdr *uh; int err; - err = make_writable(skb, skb_transport_offset(skb) + - sizeof(struct udphdr)); + err = skb_ensure_writable(skb, skb_transport_offset(skb) + + sizeof(struct udphdr)); if (unlikely(err)) return err; uh = udp_hdr(skb); - if (udp_port_key->udp_src != uh->source) + if (udp_port_key->udp_src != uh->source) { set_udp_port(skb, &uh->source, udp_port_key->udp_src); + key->tp.src = udp_port_key->udp_src; + } - if (udp_port_key->udp_dst != uh->dest) + if (udp_port_key->udp_dst != uh->dest) { set_udp_port(skb, &uh->dest, udp_port_key->udp_dst); + key->tp.dst = udp_port_key->udp_dst; + } return 0; } -static int set_tcp(struct sk_buff *skb, const struct ovs_key_tcp *tcp_port_key) +static int set_tcp(struct sk_buff *skb, struct sw_flow_key *key, + const struct ovs_key_tcp *tcp_port_key) { struct tcphdr *th; int err; - err = make_writable(skb, skb_transport_offset(skb) + - sizeof(struct tcphdr)); + err = skb_ensure_writable(skb, skb_transport_offset(skb) + + sizeof(struct tcphdr)); if (unlikely(err)) return err; th = tcp_hdr(skb); - if (tcp_port_key->tcp_src != th->source) + if (tcp_port_key->tcp_src != th->source) { set_tp_port(skb, &th->source, tcp_port_key->tcp_src, &th->check); + key->tp.src = tcp_port_key->tcp_src; + } - if (tcp_port_key->tcp_dst != th->dest) + if (tcp_port_key->tcp_dst != th->dest) { set_tp_port(skb, &th->dest, tcp_port_key->tcp_dst, &th->check); + key->tp.dst = tcp_port_key->tcp_dst; + } return 0; } -static int set_sctp(struct sk_buff *skb, - const struct ovs_key_sctp *sctp_port_key) +static int set_sctp(struct sk_buff *skb, struct sw_flow_key *key, + const struct ovs_key_sctp *sctp_port_key) { struct sctphdr *sh; int err; unsigned int sctphoff = skb_transport_offset(skb); - err = make_writable(skb, sctphoff + sizeof(struct sctphdr)); + err = skb_ensure_writable(skb, sctphoff + sizeof(struct sctphdr)); if (unlikely(err)) return err; @@ -458,39 +522,35 @@ static int set_sctp(struct sk_buff *skb, sh->checksum = old_csum ^ old_correct_csum ^ new_csum; skb_clear_hash(skb); + key->tp.src = sctp_port_key->sctp_src; + key->tp.dst = sctp_port_key->sctp_dst; } return 0; } -static int do_output(struct datapath *dp, struct sk_buff *skb, int out_port) +static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port) { - struct vport *vport; - - if (unlikely(!skb)) - return -ENOMEM; + struct vport *vport = ovs_vport_rcu(dp, out_port); - vport = ovs_vport_rcu(dp, out_port); - if (unlikely(!vport)) { + if (likely(vport)) + ovs_vport_send(vport, skb); + else kfree_skb(skb); - return -ENODEV; - } - - ovs_vport_send(vport, skb); - return 0; } static int output_userspace(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *attr) { + struct ovs_tunnel_info info; struct dp_upcall_info upcall; const struct nlattr *a; int rem; upcall.cmd = OVS_PACKET_CMD_ACTION; - upcall.key = key; upcall.userdata = NULL; upcall.portid = 0; + upcall.egress_tun_info = NULL; for (a = nla_data(attr), rem = nla_len(attr); rem > 0; a = nla_next(a, &rem)) { @@ -502,15 +562,27 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, case OVS_USERSPACE_ATTR_PID: upcall.portid = nla_get_u32(a); break; + + case OVS_USERSPACE_ATTR_EGRESS_TUN_PORT: { + /* Get out tunnel info. */ + struct vport *vport; + + vport = ovs_vport_rcu(dp, nla_get_u32(a)); + if (vport) { + int err; + + err = ovs_vport_get_egress_tun_info(vport, skb, + &info); + if (!err) + upcall.egress_tun_info = &info; + } + break; } - } - return ovs_dp_upcall(dp, skb, &upcall); -} + } /* End of switch. */ + } -static bool last_action(const struct nlattr *a, int rem) -{ - return a->nla_len == rem; + return ovs_dp_upcall(dp, skb, key, &upcall); } static int sample(struct datapath *dp, struct sk_buff *skb, @@ -547,7 +619,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb, * user space. This skb will be consumed by its caller. */ if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE && - last_action(a, rem))) + nla_is_last(a, rem))) return output_userspace(dp, skb, key, a); skb = skb_clone(skb, GFP_ATOMIC); @@ -580,18 +652,20 @@ static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key, key->ovs_flow_hash = hash; } -static int execute_set_action(struct sk_buff *skb, - const struct nlattr *nested_attr) +static int execute_set_action(struct sk_buff *skb, struct sw_flow_key *key, + const struct nlattr *nested_attr) { int err = 0; switch (nla_type(nested_attr)) { case OVS_KEY_ATTR_PRIORITY: skb->priority = nla_get_u32(nested_attr); + key->phy.priority = skb->priority; break; case OVS_KEY_ATTR_SKB_MARK: skb->mark = nla_get_u32(nested_attr); + key->phy.skb_mark = skb->mark; break; case OVS_KEY_ATTR_TUNNEL_INFO: @@ -599,27 +673,31 @@ static int execute_set_action(struct sk_buff *skb, break; case OVS_KEY_ATTR_ETHERNET: - err = set_eth_addr(skb, nla_data(nested_attr)); + err = set_eth_addr(skb, key, nla_data(nested_attr)); break; case OVS_KEY_ATTR_IPV4: - err = set_ipv4(skb, nla_data(nested_attr)); + err = set_ipv4(skb, key, nla_data(nested_attr)); break; case OVS_KEY_ATTR_IPV6: - err = set_ipv6(skb, nla_data(nested_attr)); + err = set_ipv6(skb, key, nla_data(nested_attr)); break; case OVS_KEY_ATTR_TCP: - err = set_tcp(skb, nla_data(nested_attr)); + err = set_tcp(skb, key, nla_data(nested_attr)); break; case OVS_KEY_ATTR_UDP: - err = set_udp(skb, nla_data(nested_attr)); + err = set_udp(skb, key, nla_data(nested_attr)); break; case OVS_KEY_ATTR_SCTP: - err = set_sctp(skb, nla_data(nested_attr)); + err = set_sctp(skb, key, nla_data(nested_attr)); + break; + + case OVS_KEY_ATTR_MPLS: + err = set_mpls(skb, key, nla_data(nested_attr)); break; } @@ -631,13 +709,17 @@ static int execute_recirc(struct datapath *dp, struct sk_buff *skb, const struct nlattr *a, int rem) { struct deferred_action *da; - int err; - err = ovs_flow_key_update(skb, key); - if (err) - return err; + if (!is_flow_key_valid(key)) { + int err; + + err = ovs_flow_key_update(skb, key); + if (err) + return err; + } + BUG_ON(!is_flow_key_valid(key)); - if (!last_action(a, rem)) { + if (!nla_is_last(a, rem)) { /* Recirc action is the not the last action * of the action list, need to clone the skb. */ @@ -672,7 +754,8 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, /* Every output action needs a separate clone of 'skb', but the common * case is just a single output action, so that doing a clone and * then freeing the original skbuff is wasteful. So the following code - * is slightly obscure just to avoid that. */ + * is slightly obscure just to avoid that. + */ int prev_port = -1; const struct nlattr *a; int rem; @@ -681,8 +764,12 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, a = nla_next(a, &rem)) { int err = 0; - if (prev_port != -1) { - do_output(dp, skb_clone(skb, GFP_ATOMIC), prev_port); + if (unlikely(prev_port != -1)) { + struct sk_buff *out_skb = skb_clone(skb, GFP_ATOMIC); + + if (out_skb) + do_output(dp, out_skb, prev_port); + prev_port = -1; } @@ -699,19 +786,25 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, execute_hash(skb, key, a); break; + case OVS_ACTION_ATTR_PUSH_MPLS: + err = push_mpls(skb, key, nla_data(a)); + break; + + case OVS_ACTION_ATTR_POP_MPLS: + err = pop_mpls(skb, key, nla_get_be16(a)); + break; + case OVS_ACTION_ATTR_PUSH_VLAN: - err = push_vlan(skb, nla_data(a)); - if (unlikely(err)) /* skb already freed. */ - return err; + err = push_vlan(skb, key, nla_data(a)); break; case OVS_ACTION_ATTR_POP_VLAN: - err = pop_vlan(skb); + err = pop_vlan(skb, key); break; case OVS_ACTION_ATTR_RECIRC: err = execute_recirc(dp, skb, key, a, rem); - if (last_action(a, rem)) { + if (nla_is_last(a, rem)) { /* If this is the last action, the skb has * been consumed or freed. * Return immediately. @@ -721,7 +814,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, break; case OVS_ACTION_ATTR_SET: - err = execute_set_action(skb, nla_data(a)); + err = execute_set_action(skb, key, nla_data(a)); break; case OVS_ACTION_ATTR_SAMPLE: @@ -771,14 +864,12 @@ static void process_deferred_actions(struct datapath *dp) /* Execute a list of actions against 'skb'. */ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb, + const struct sw_flow_actions *acts, struct sw_flow_key *key) { int level = this_cpu_read(exec_actions_level); - struct sw_flow_actions *acts; int err; - acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts); - this_cpu_inc(exec_actions_level); OVS_CB(skb)->egress_tun_info = NULL; err = do_execute_actions(dp, skb, key, |