Datapath: Change in openvswitch kernel module to support MPLS label depth of 3 in...

Upstream commit:
    commit fbdcdd78da7c95f1b970d371e1b23cbd3aa990f3
    Author: Martin Varghese <martin.varghese@nokia.com>
    Date:   Mon Nov 4 07:27:44 2019 +0530

    Change in Openvswitch to support MPLS label depth of 3 in ingress
    direction

    The openvswitch was supporting a MPLS label depth of 1 in the
    ingress direction though the userspace OVS supports a max depth
    of 3 labels.This change enables openvswitch module to support a
    max depth of 3 labels in the ingress.

    Signed-off-by: Martin Varghese <martin.varghese@nokia.com>
    Acked-by: Pravin B Shelar <pshelar@ovn.org>
    Signed-off-by: David S. Miller <davem@davemloft.net>
Tested-by: Greg Rose <gvrose8192@gmail.com>
Reviewed-by: Greg Rose <gvrose8192@gmail.com>
Signed-off-by: Martin Varghese <martin.varghese@nokia.com>
Signed-off-by: Ben Pfaff <blp@ovn.org>

diff --git a/datapath/actions.c b/datapath/actions.c
index a44e8046bc7754fd2a7c496a1eec8d4f35bfe1b8..fbf4457037eaecef0746a7390506ab8c42f3b201 100644 (file)
--- a/datapath/actions.c
+++ b/datapath/actions.c
@@ -276,7 +276,7 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
        }
 
        stack->label_stack_entry = lse;
-       flow_key->mpls.top_lse = lse;
+       flow_key->mpls.lse[0] = lse;
        return 0;
 }
 

diff --git a/datapath/flow.c b/datapath/flow.c
index 916f7f457ff7c3e53db0459f639293063469eaa5..6dc7402d50902a0c310c870c39620d2414a295b8 100644 (file)
--- a/datapath/flow.c
+++ b/datapath/flow.c
@@ -659,27 +659,35 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key)
                        memset(&key->ipv4, 0, sizeof(key->ipv4));
                }
        } else if (eth_p_mpls(key->eth.type)) {
-               size_t stack_len = MPLS_HLEN;
+               u8 label_count = 1;
 
+               memset(&key->mpls, 0, sizeof(key->mpls));
                skb_set_inner_network_header(skb, skb->mac_len);
                while (1) {
                        __be32 lse;
 
-                       error = check_header(skb, skb->mac_len + stack_len);
+                       error = check_header(skb, skb->mac_len +
+                                            label_count * MPLS_HLEN);
                        if (unlikely(error))
                                return 0;
 
                        memcpy(&lse, skb_inner_network_header(skb), MPLS_HLEN);
 
-                       if (stack_len == MPLS_HLEN)
-                               memcpy(&key->mpls.top_lse, &lse, MPLS_HLEN);
+                       if (label_count <= MPLS_LABEL_DEPTH)
+                               memcpy(&key->mpls.lse[label_count - 1], &lse,
+                                      MPLS_HLEN);
 
-                       skb_set_inner_network_header(skb, skb->mac_len + stack_len);
+                       skb_set_inner_network_header(skb, skb->mac_len +
+                                                    label_count * MPLS_HLEN);
                        if (lse & htonl(MPLS_LS_S_MASK))
                                break;
 
-                       stack_len += MPLS_HLEN;
+                       label_count++;
                }
+               if (label_count > MPLS_LABEL_DEPTH)
+                       label_count = MPLS_LABEL_DEPTH;
+
+               key->mpls.num_labels_mask = GENMASK(label_count - 1, 0);
        } else if (key->eth.type == htons(ETH_P_IPV6)) {
                int nh_len;             /* IPv6 Header + Extensions */
 

diff --git a/datapath/flow.h b/datapath/flow.h
index 55603002dedb1f73975174db1317334251c070a3..4ad5363e3450088b634b4ea0f0819cc86030e86b 100644 (file)
--- a/datapath/flow.h
+++ b/datapath/flow.h
@@ -43,6 +43,7 @@ enum sw_flow_mac_proto {
        MAC_PROTO_ETHERNET,
 };
 #define SW_FLOW_KEY_INVALID    0x80
+#define MPLS_LABEL_DEPTH       3
 
 /* Store options at the end of the array if they are less than the
  * maximum size. This allows us to get the benefits of variable length
@@ -97,9 +98,6 @@ struct sw_flow_key {
                                         * protocol.
                                         */
        union {
-               struct {
-                       __be32 top_lse; /* top label stack entry */
-               } mpls;
                struct {
                        u8     proto;   /* IP protocol or lower 8 bits of ARP opcode. */
                        u8     tos;         /* IP ToS. */
@@ -148,6 +146,10 @@ struct sw_flow_key {
                                } nd;
                        };
                } ipv6;
+               struct {
+                       u32 num_labels_mask;    /* labels present bitmap of effective length MPLS_LABEL_DEPTH */
+                       __be32 lse[MPLS_LABEL_DEPTH];     /* label stack entry  */
+               } mpls;
                struct ovs_key_nsh nsh;         /* network service header */
        };
        struct {

diff --git a/datapath/flow_netlink.c b/datapath/flow_netlink.c
index 35f13d753ceca626a73890f9ae8bc9d2f4fe9878..9fc1a19221d0e0a03f1dcce49ace62dd2f97139c 100644 (file)
--- a/datapath/flow_netlink.c
+++ b/datapath/flow_netlink.c
@@ -438,7 +438,7 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
        [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) },
+       [OVS_KEY_ATTR_MPLS]      = { .len = OVS_ATTR_VARIABLE },
        [OVS_KEY_ATTR_CT_STATE]  = { .len = sizeof(u32) },
        [OVS_KEY_ATTR_CT_ZONE]   = { .len = sizeof(u16) },
        [OVS_KEY_ATTR_CT_MARK]   = { .len = sizeof(u32) },
@@ -1619,10 +1619,27 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match,
 
        if (attrs & (1ULL << OVS_KEY_ATTR_MPLS)) {
                const struct ovs_key_mpls *mpls_key;
+               u32 hdr_len;
+               u32 label_count, label_count_mask, i;
+
 
                mpls_key = nla_data(a[OVS_KEY_ATTR_MPLS]);
-               SW_FLOW_KEY_PUT(match, mpls.top_lse,
-                               mpls_key->mpls_lse, is_mask);
+               hdr_len = nla_len(a[OVS_KEY_ATTR_MPLS]);
+               label_count = hdr_len / sizeof(struct ovs_key_mpls);
+
+               if (label_count == 0 || label_count > MPLS_LABEL_DEPTH ||
+                   hdr_len % sizeof(struct ovs_key_mpls))
+                       return -EINVAL;
+
+               label_count_mask =  GENMASK(label_count - 1, 0);
+
+               for (i = 0 ; i < label_count; i++)
+                       SW_FLOW_KEY_PUT(match, mpls.lse[i],
+                                       mpls_key[i].mpls_lse, is_mask);
+
+               SW_FLOW_KEY_PUT(match, mpls.num_labels_mask,
+                               label_count_mask, is_mask);
+
 
                attrs &= ~(1ULL << OVS_KEY_ATTR_MPLS);
        }
@@ -2104,13 +2121,18 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
                ether_addr_copy(arp_key->arp_sha, output->ipv4.arp.sha);
                ether_addr_copy(arp_key->arp_tha, output->ipv4.arp.tha);
        } else if (eth_p_mpls(swkey->eth.type)) {
+               u8 num_labels, i;
                struct ovs_key_mpls *mpls_key;
 
-               nla = nla_reserve(skb, OVS_KEY_ATTR_MPLS, sizeof(*mpls_key));
+               num_labels = hweight_long(output->mpls.num_labels_mask);
+               nla = nla_reserve(skb, OVS_KEY_ATTR_MPLS,
+                                 num_labels * sizeof(*mpls_key));
                if (!nla)
                        goto nla_put_failure;
+
                mpls_key = nla_data(nla);
-               mpls_key->mpls_lse = output->mpls.top_lse;
+               for (i = 0; i < num_labels; i++)
+                       mpls_key[i].mpls_lse = output->mpls.lse[i];
        }
 
        if ((swkey->eth.type == htons(ETH_P_IP) ||
@@ -2400,13 +2422,14 @@ static inline void add_nested_action_end(struct sw_flow_actions *sfa,
 static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
                                  const struct sw_flow_key *key,
                                  struct sw_flow_actions **sfa,
-                                 __be16 eth_type, __be16 vlan_tci, bool log);
+                                 __be16 eth_type, __be16 vlan_tci,
+                                 u32 mpls_label_count, bool log);
 
 static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
                                    const struct sw_flow_key *key,
                                    struct sw_flow_actions **sfa,
                                    __be16 eth_type, __be16 vlan_tci,
-                                   bool log, bool last)
+                                   u32 mpls_label_count, bool log, bool last)
 {
        const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
        const struct nlattr *probability, *actions;
@@ -2457,7 +2480,7 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
                return err;
 
        err = __ovs_nla_copy_actions(net, actions, key, sfa,
-                                    eth_type, vlan_tci, log);
+                                    eth_type, vlan_tci, mpls_label_count, log);
 
        if (err)
                return err;
@@ -2472,7 +2495,7 @@ static int validate_and_copy_clone(struct net *net,
                                   const struct sw_flow_key *key,
                                   struct sw_flow_actions **sfa,
                                   __be16 eth_type, __be16 vlan_tci,
-                                  bool log, bool last)
+                                  u32 mpls_label_count, bool log, bool last)
 {
        int start, err;
        u32 exec;
@@ -2492,7 +2515,7 @@ static int validate_and_copy_clone(struct net *net,
                return err;
 
        err = __ovs_nla_copy_actions(net, attr, key, sfa,
-                                    eth_type, vlan_tci, log);
+                                    eth_type, vlan_tci, mpls_label_count, log);
        if (err)
                return err;
 
@@ -2859,6 +2882,7 @@ static int validate_and_copy_check_pkt_len(struct net *net,
                                           const struct sw_flow_key *key,
                                           struct sw_flow_actions **sfa,
                                           __be16 eth_type, __be16 vlan_tci,
+                                          u32 mpls_label_count,
                                           bool log, bool last)
 {
        const struct nlattr *acts_if_greater, *acts_if_lesser_eq;
@@ -2906,7 +2930,7 @@ static int validate_and_copy_check_pkt_len(struct net *net,
                return nested_acts_start;
 
        err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa,
-                                    eth_type, vlan_tci, log);
+                                    eth_type, vlan_tci, mpls_label_count, log);
 
        if (err)
                return err;
@@ -2919,7 +2943,7 @@ static int validate_and_copy_check_pkt_len(struct net *net,
                return nested_acts_start;
 
        err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa,
-                                    eth_type, vlan_tci, log);
+                                    eth_type, vlan_tci, mpls_label_count, log);
 
        if (err)
                return err;
@@ -2946,7 +2970,8 @@ static int copy_action(const struct nlattr *from,
 static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
                                  const struct sw_flow_key *key,
                                  struct sw_flow_actions **sfa,
-                                 __be16 eth_type, __be16 vlan_tci, bool log)
+                                 __be16 eth_type, __be16 vlan_tci,
+                                 u32 mpls_label_count, bool log)
 {
        u8 mac_proto = ovs_key_mac_proto(key);
        const struct nlattr *a;
@@ -3059,26 +3084,35 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
                             !eth_p_mpls(eth_type)))
                                return -EINVAL;
                        eth_type = mpls->mpls_ethertype;
+                       mpls_label_count++;
                        break;
                }
 
-               case OVS_ACTION_ATTR_POP_MPLS:
+               case OVS_ACTION_ATTR_POP_MPLS: {
+                       __be16  proto;
                        if (vlan_tci & htons(VLAN_CFI_MASK) ||
                            !eth_p_mpls(eth_type))
                                return -EINVAL;
 
-                       /* Disallow subsequent L2.5+ set and mpls_pop actions
-                        * as there is no check here to ensure that the new
-                        * eth_type is valid and thus set actions could
-                        * write off the end of the packet or otherwise
-                        * corrupt it.
+                       /* Disallow subsequent L2.5+ set actions and mpls_pop
+                        * actions once the last MPLS label in the packet is
+                        * popped as there is no check here to ensure that
+                        * the new eth type is valid and thus set actions could
+                        * write off the end of the packet or otherwise corrupt
+                        * it.
                         *
                         * Support for these actions is planned using packet
                         * recirculation.
                         */
-                       eth_type = htons(0);
-                       break;
+                       proto = nla_get_be16(a);
+                       mpls_label_count--;
 
+                       if (!eth_p_mpls(proto) || !mpls_label_count)
+                               eth_type = htons(0);
+                       else
+                               eth_type =  proto;
+                       break;
+               }
                case OVS_ACTION_ATTR_SET:
                        err = validate_set(a, key, sfa,
                                           &skip_copy, mac_proto, eth_type,
@@ -3100,6 +3134,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 
                        err = validate_and_copy_sample(net, a, key, sfa,
                                                       eth_type, vlan_tci,
+                                                      mpls_label_count,
                                                       log, last);
                        if (err)
                                return err;
@@ -3170,6 +3205,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 
                        err = validate_and_copy_clone(net, a, key, sfa,
                                                      eth_type, vlan_tci,
+                                                     mpls_label_count,
                                                      log, last);
                        if (err)
                                return err;
@@ -3183,6 +3219,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
                         err = validate_and_copy_check_pkt_len(net, a, key, sfa,
                                                               eth_type,
                                                               vlan_tci, log,
+                                                             mpls_label_count,
                                                               last);
                         if (err)
                                 return err;
@@ -3213,14 +3250,18 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
                         struct sw_flow_actions **sfa, bool log)
 {
        int err;
+       u32 mpls_label_count = 0;
 
        *sfa = nla_alloc_flow_actions(min(nla_len(attr), MAX_ACTIONS_BUFSIZE));
        if (IS_ERR(*sfa))
                return PTR_ERR(*sfa);
 
+       if (eth_p_mpls(key->eth.type))
+               mpls_label_count = hweight_long(key->mpls.num_labels_mask);
+
        (*sfa)->orig_len = nla_len(attr);
        err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type,
-                                    key->eth.vlan.tci, log);
+                                    key->eth.vlan.tci, mpls_label_count, log);
        if (err)
                ovs_nla_free_flow_actions(*sfa);
 

diff --git a/tests/system-traffic.at b/tests/system-traffic.at
index 870a05efe04c0c9751d1cc074a3ed3c4acfe2261..cde7429f3304789c8adc24a1c144dccd78d2f8ad 100644 (file)
--- a/tests/system-traffic.at
+++ b/tests/system-traffic.at
@@ -992,6 +992,45 @@ NS_CHECK_EXEC([at_ns1], [ping -q -c 3 -i 0.3 -w 2 10.1.1.1 | FORMAT_PING], [0],
 
 OVS_TRAFFIC_VSWITCHD_STOP
 AT_CLEANUP
+
+AT_SETUP([datapath - multiple mpls label pop])
+OVS_TRAFFIC_VSWITCHD_START([_ADD_BR([br1])])
+
+ADD_NAMESPACES(at_ns0, at_ns1)
+
+ADD_VETH(p0, at_ns0, br0, "10.1.1.1/24")
+ADD_VETH(p1, at_ns1, br1, "10.1.1.2/24")
+
+AT_CHECK([ip link add patch0 type veth peer name patch1])
+on_exit 'ip link del patch0'
+
+AT_CHECK([ip link set dev patch0 up])
+AT_CHECK([ip link set dev patch1 up])
+AT_CHECK([ovs-vsctl add-port br0 patch0])
+AT_CHECK([ovs-vsctl add-port br1 patch1])
+
+AT_DATA([flows.txt], [dnl
+table=0,priority=100,dl_type=0x0800 actions=push_mpls:0x8847,set_mpls_label:3,push_mpls:0x8847,set_mpls_label:2,push_mpls:0x8847,set_mpls_label:1,resubmit(,3)
+table=0,priority=100,dl_type=0x8847,mpls_label=1 actions=pop_mpls:0x8847,resubmit(,1)
+table=1,priority=100,dl_type=0x8847,mpls_label=2 actions=pop_mpls:0x8847,resubmit(,2)
+table=2,priority=100,dl_type=0x8847,mpls_label=3 actions=pop_mpls:0x0800,resubmit(,3)
+table=0,priority=10 actions=resubmit(,3)
+table=3,priority=10 actions=normal
+])
+
+AT_CHECK([ovs-ofctl add-flows br0 flows.txt])
+AT_CHECK([ovs-ofctl add-flows br1 flows.txt])
+
+NS_CHECK_EXEC([at_ns0], [ping -q -c 3 -i 0.3 -w 2 10.1.1.2 | FORMAT_PING], [0], [dnl
+3 packets transmitted, 3 received, 0% packet loss, time 0ms
+])
+
+NS_CHECK_EXEC([at_ns1], [ping -q -c 3 -i 0.3 -w 2 10.1.1.1 | FORMAT_PING], [0], [dnl
+3 packets transmitted, 3 received, 0% packet loss, time 0ms
+])
+OVS_TRAFFIC_VSWITCHD_STOP
+AT_CLEANUP
+
 AT_SETUP([datapath - basic truncate action])
 AT_SKIP_IF([test $HAVE_NC = no])
 OVS_TRAFFIC_VSWITCHD_START()