userspace: Handling of versatile tunnel ports

In netdev_gre_build_header(), GRE protocol and VXLAN next_potocol is set based on packet_type of flow. If it's about an Ethernet packet, it is set to ETP_TYPE_TEB. Otherwise, if the name space is OFPHTN_ETHERNET, it is set according to the name space type. Signed-off-by: Jan Scheurich <[email protected]> Signed-off-by: Ben Pfaff <[email protected]>
lhh · Jun 27, 2017 · 875ab13 · 875ab13
1 parent 3d4b2e6
commit 875ab13
Show file tree

Hide file tree

Showing 18 changed files with 280 additions and 102 deletions.
diff --git a/NEWS b/NEWS
@@ -59,11 +59,9 @@ Post-v2.7.0
      * OVN services are no longer restarted automatically after upgrade.
    - Add --cleanup option to command 'ovs-appctl exit' (see ovs-vswitchd(8)).
    - L3 tunneling:
-     * Add "layer3" options for tunnel ports that support non-Ethernet (L3)
-       payload (GRE, VXLAN-GPE).
+     * Use new tunnel port option "packet_type" to configure L2 vs. L3.
      * New vxlan tunnel extension "gpe" to support VXLAN-GPE tunnels.
-     * Transparently pop and push Ethernet headers at transmit/reception
-       of packets to/from L3 tunnels.
+     * New support for non-Ethernet (L3) payloads in GRE and VXLAN-GPE.
    - The BFD detection multiplier is now user-configurable.
    - Add experimental support for hardware offloading
      * HW offloading is disabled by default.

diff --git a/lib/meta-flow.xml b/lib/meta-flow.xml
@@ -26,19 +26,27 @@
     networking technology in use are called called <dfn>root fields</dfn>.
     Open vSwitch 2.7 and earlier considered Ethernet fields to be root fields,
     and this remains the default mode of operation for Open vSwitch bridges.
-    In this mode, when a packet is received from a non-Ethernet interfaces,
-    such as a layer-3 LISP or GRE tunnel, Open vSwitch force-fits it to this
+    When a packet is received from a non-Ethernet interfaces, such as a layer-3
+    LISP tunnel, Open vSwitch 2.7 and earlier force-fit the packet to this
     Ethernet-centric point of view by pretending that an Ethernet header is
     present whose Ethernet type that indicates the packet's actual type (and
     whose source and destination addresses are all-zero).
   </p>
 
   <p>
-    Open vSwitch 2.8 and later supports the ``packet type-aware pipeline''
-    concept introduced in OpenFlow 1.5.  A bridge configured to be packet
-    type-aware can handle packets of multiple networking technologies, such as
-    Ethernet, IP, ARP, MPLS, or NSH in parallel.  Such a bridge does not have
-    any root fields.
+    Open vSwitch 2.8 and later implement the ``packet type-aware pipeline''
+    concept introduced in OpenFlow 1.5.  Such a pipeline does not have any root
+    fields.  Instead, a new metadata field, <ref field="packet_type"/>,
+    indicates the basic type of the packet, which can be Ethernet, IPv4, IPv6,
+    or another type.  For backward compatibility, by default Open vSwitch 2.8
+    imitates the behavior of Open vSwitch 2.7 and earlier.  Later versions of
+    Open vSwitch may change the default, and in the meantime controllers can
+    turn off this legacy behavior, on a port-by-port basis, by setting
+    <code>options:packet_type</code> to <code>ptap</code> in the
+    <code>Interface</code> table.  This is significant only for ports that can
+    handle non-Ethernet packets, which is currently just LISP, VXLAN-GPE, and
+    GRE tunnel ports.  See <code>ovs-vwitchd.conf.db</code>(5) for more
+    information.
   </p>
 
   <p>
@@ -332,14 +340,6 @@ tcp,tp_src=0x07c0/0xfff0
     <dt><code>mplsm</code></dt>  <dd><code>eth_type=0x8848</code></dd>
   </dl>
 
-  <p>
-    These shorthand notations continue to work in packet type-aware bridges.
-    The absence of a packet_type match implies
-    <code>packet_type=ethernet</code>, so that shorthands match on Ethernet
-    packets with the implied eth_type. Please note that the shorthand
-    <code>ip</code> does not match packets of packet_type (1,0x800) for IPv4.
-  </p>
-
 
   <h2>Evolution of OpenFlow Fields</h2>
 

diff --git a/lib/netdev-bsd.c b/lib/netdev-bsd.c
@@ -1517,6 +1517,7 @@ netdev_bsd_update_flags(struct netdev *netdev_, enum netdev_flags off,
                                                      \
     GET_FEATURES,                                    \
     NULL, /* set_advertisement */                    \
+    NULL, /* get_pt_mode */                          \
     NULL, /* set_policing */                         \
     NULL, /* get_qos_type */                         \
     NULL, /* get_qos_capabilities */                 \

diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c
@@ -3276,6 +3276,7 @@ netdev_dpdk_vhost_client_reconfigure(struct netdev *netdev)
     GET_STATS,                                                \
     GET_FEATURES,                                             \
     NULL,                       /* set_advertisements */      \
+    NULL,                       /* get_pt_mode */             \
                                                               \
     netdev_dpdk_set_policing,                                 \
     netdev_dpdk_get_qos_types,                                \

diff --git a/lib/netdev-dummy.c b/lib/netdev-dummy.c
@@ -1382,6 +1382,7 @@ netdev_dummy_update_flags(struct netdev *netdev_,
                                                                 \
     NULL,                       /* get_features */              \
     NULL,                       /* set_advertisements */        \
+    NULL,                       /* get_pt_mode */               \
                                                                 \
     NULL,                       /* set_policing */              \
     NULL,                       /* get_qos_types */             \

diff --git a/lib/netdev-linux.c b/lib/netdev-linux.c
@@ -2843,6 +2843,7 @@ netdev_linux_update_flags(struct netdev *netdev_, enum netdev_flags off,
                                                                 \
     GET_FEATURES,                                               \
     netdev_linux_set_advertisements,                            \
+    NULL,                       /* get_pt_mode */               \
                                                                 \
     netdev_linux_set_policing,                                  \
     netdev_linux_get_qos_types,                                 \

diff --git a/lib/netdev-native-tnl.c b/lib/netdev-native-tnl.c
@@ -463,10 +463,13 @@ netdev_gre_build_header(const struct netdev *netdev,
 
     greh = netdev_tnl_ip_build_header(data, params, IPPROTO_GRE);
 
-    if (tnl_cfg->is_layer3) {
-        greh->protocol = params->flow->dl_type;
-    } else {
+    if (params->flow->packet_type == htonl(PT_ETH)) {
         greh->protocol = htons(ETH_TYPE_TEB);
+    } else if (pt_ns(params->flow->packet_type) == OFPHTN_ETHERTYPE) {
+        greh->protocol = pt_ns_type_be(params->flow->packet_type);
+    } else {
+        ovs_mutex_unlock(&dev->mutex);
+        return 1;
     }
     greh->flags = 0;
 
@@ -575,8 +578,10 @@ netdev_vxlan_build_header(const struct netdev *netdev,
         put_16aligned_be32(&vxh->vx_flags, htonl(VXLAN_FLAGS | VXLAN_HF_GPE));
         put_16aligned_be32(&vxh->vx_vni,
                            htonl(ntohll(params->flow->tunnel.tun_id) << 8));
-        if (tnl_cfg->is_layer3) {
-            switch (ntohs(params->flow->dl_type)) {
+        if (params->flow->packet_type == htonl(PT_ETH)) {
+            vxh->vx_gpe.next_protocol = VXLAN_GPE_NP_ETHERNET;
+        } else if (pt_ns(params->flow->packet_type) == OFPHTN_ETHERTYPE) {
+            switch (pt_ns_type(params->flow->packet_type)) {
             case ETH_TYPE_IP:
                 vxh->vx_gpe.next_protocol = VXLAN_GPE_NP_IPV4;
                 break;
@@ -586,9 +591,11 @@ netdev_vxlan_build_header(const struct netdev *netdev,
             case ETH_TYPE_TEB:
                 vxh->vx_gpe.next_protocol = VXLAN_GPE_NP_ETHERNET;
                 break;
+            default:
+                goto drop;
             }
         } else {
-            vxh->vx_gpe.next_protocol = VXLAN_GPE_NP_ETHERNET;
+            goto drop;
         }
     } else {
         put_16aligned_be32(&vxh->vx_flags, htonl(VXLAN_FLAGS));
@@ -600,6 +607,10 @@ netdev_vxlan_build_header(const struct netdev *netdev,
     data->header_len += sizeof *vxh;
     data->tnl_type = OVS_VPORT_TYPE_VXLAN;
     return 0;
+
+drop:
+    ovs_mutex_unlock(&dev->mutex);
+    return 1;
 }
 
 struct dp_packet *

diff --git a/lib/netdev-provider.h b/lib/netdev-provider.h
@@ -474,6 +474,12 @@ struct netdev_class {
     int (*set_advertisements)(struct netdev *netdev,
                               enum netdev_features advertise);
 
+    /* Returns 'netdev''s configured packet_type mode.
+     *
+     * This function may be set to null if it would always return
+     * NETDEV_PT_LEGACY_L2. */
+    enum netdev_pt_mode (*get_pt_mode)(const struct netdev *netdev);
+
     /* Attempts to set input rate limiting (policing) policy, such that up to
      * 'kbits_rate' kbps of traffic is accepted, with a maximum accumulative
      * burst size of 'kbits' kb.

diff --git a/lib/netdev-vport.c b/lib/netdev-vport.c
@@ -98,18 +98,6 @@ netdev_vport_is_patch(const struct netdev *netdev)
     return class->get_config == get_patch_config;
 }
 
-bool
-netdev_vport_is_layer3(const struct netdev *dev)
-{
-    if (is_vport_class(netdev_get_class(dev))) {
-        struct netdev_vport *vport = netdev_vport_cast(dev);
-
-        return vport->tnl_cfg.is_layer3;
-    }
-
-    return false;
-}
-
 static bool
 netdev_vport_needs_dst_port(const struct netdev *dev)
 {
@@ -407,23 +395,45 @@ parse_tunnel_ip(const char *value, bool accept_mcast, bool *flow,
     return 0;
 }
 
+enum tunnel_layers {
+    TNL_L2 = 1 << 0,       /* 1 if a tunnel type can carry Ethernet traffic. */
+    TNL_L3 = 1 << 1        /* 1 if a tunnel type can carry L3 traffic. */
+};
+static enum tunnel_layers
+tunnel_supported_layers(const char *type,
+                        const struct netdev_tunnel_config *tnl_cfg)
+{
+    if (!strcmp(type, "lisp")) {
+        return TNL_L3;
+    } else if (!strcmp(type, "gre")) {
+        return TNL_L2 | TNL_L3;
+    } else if (!strcmp(type, "vxlan") && tnl_cfg->exts & OVS_VXLAN_EXT_GPE) {
+        return TNL_L2 | TNL_L3;
+    } else {
+        return TNL_L2;
+    }
+}
+static enum netdev_pt_mode
+default_pt_mode(enum tunnel_layers layers)
+{
+    return layers == TNL_L3 ? NETDEV_PT_LEGACY_L3 : NETDEV_PT_LEGACY_L2;
+}
+
 static int
 set_tunnel_config(struct netdev *dev_, const struct smap *args, char **errp)
 {
     struct netdev_vport *dev = netdev_vport_cast(dev_);
     const char *name = netdev_get_name(dev_);
     const char *type = netdev_get_type(dev_);
     struct ds errors = DS_EMPTY_INITIALIZER;
-    bool needs_dst_port, has_csum, optional_layer3;
+    bool needs_dst_port, has_csum;
     uint16_t dst_proto = 0, src_proto = 0;
     struct netdev_tunnel_config tnl_cfg;
     struct smap_node *node;
-    bool is_layer3 = false;
     int err;
 
     has_csum = strstr(type, "gre") || strstr(type, "geneve") ||
                strstr(type, "stt") || strstr(type, "vxlan");
-    optional_layer3 = !strcmp(type, "gre");
     memset(&tnl_cfg, 0, sizeof tnl_cfg);
 
     /* Add a default destination port for tunnel ports if none specified. */
@@ -437,7 +447,6 @@ set_tunnel_config(struct netdev *dev_, const struct smap *args, char **errp)
 
     if (!strcmp(type, "lisp")) {
         tnl_cfg.dst_port = htons(LISP_DST_PORT);
-        tnl_cfg.is_layer3 = true;
     }
 
     if (!strcmp(type, "stt")) {
@@ -501,9 +510,10 @@ set_tunnel_config(struct netdev *dev_, const struct smap *args, char **errp)
             }
         } else if (!strcmp(node->key, "key") ||
                    !strcmp(node->key, "in_key") ||
-                   !strcmp(node->key, "out_key")) {
+                   !strcmp(node->key, "out_key") ||
+                   !strcmp(node->key, "packet_type")) {
             /* Handled separately below. */
-        } else if (!strcmp(node->key, "exts")) {
+        } else if (!strcmp(node->key, "exts") && !strcmp(type, "vxlan")) {
             char *str = xstrdup(node->value);
             char *ext, *save_ptr = NULL;
 
@@ -515,7 +525,6 @@ set_tunnel_config(struct netdev *dev_, const struct smap *args, char **errp)
                     tnl_cfg.exts |= (1 << OVS_VXLAN_EXT_GBP);
                 } else if (!strcmp(type, "vxlan") && !strcmp(ext, "gpe")) {
                     tnl_cfg.exts |= (1 << OVS_VXLAN_EXT_GPE);
-                    optional_layer3 = true;
                 } else {
                     ds_put_format(&errors, "%s: unknown extension '%s'\n",
                                   name, ext);
@@ -528,21 +537,44 @@ set_tunnel_config(struct netdev *dev_, const struct smap *args, char **errp)
         } else if (!strcmp(node->key, "egress_pkt_mark")) {
             tnl_cfg.egress_pkt_mark = strtoul(node->value, NULL, 10);
             tnl_cfg.set_egress_pkt_mark = true;
-        } else if (!strcmp(node->key, "layer3")) {
-            if (!strcmp(node->value, "true")) {
-                is_layer3 = true;
-            }
         } else {
             ds_put_format(&errors, "%s: unknown %s argument '%s'\n", name,
                           type, node->key);
         }
     }
 
-    if (optional_layer3 && is_layer3) {
-       tnl_cfg.is_layer3 = is_layer3;
-    } else if (!optional_layer3 && is_layer3) {
-        ds_put_format(&errors, "%s: unknown %s argument '%s'\n",
-                      name, type, "layer3");
+    enum tunnel_layers layers = tunnel_supported_layers(type, &tnl_cfg);
+    const char *full_type = (strcmp(type, "vxlan") ? type
+                             : tnl_cfg.exts & OVS_VXLAN_EXT_GPE ? "VXLAN-GPE"
+                             : "VXLAN (without GPE");
+    const char *packet_type = smap_get(args, "packet_type");
+    if (!packet_type) {
+        tnl_cfg.pt_mode = default_pt_mode(layers);
+    } else if (!strcmp(packet_type, "legacy_l2")) {
+        tnl_cfg.pt_mode = NETDEV_PT_LEGACY_L2;
+        if (!(layers & TNL_L2)) {
+            ds_put_format(&errors, "%s: legacy_l2 configured on %s tunnel "
+                          "that cannot carry L2 traffic\n",
+                          name, full_type);
+            err = EINVAL;
+            goto out;
+        }
+    } else if (!strcmp(packet_type, "legacy_l3")) {
+        tnl_cfg.pt_mode = NETDEV_PT_LEGACY_L3;
+        if (!(layers & TNL_L3)) {
+            ds_put_format(&errors, "%s: legacy_l3 configured on %s tunnel "
+                          "that cannot carry L3 traffic\n",
+                          name, full_type);
+            err = EINVAL;
+            goto out;
+        }
+    } else if (!strcmp(packet_type, "ptap")) {
+        tnl_cfg.pt_mode = NETDEV_PT_AWARE;
+    } else {
+        ds_put_format(&errors, "%s: unknown packet_type '%s'\n",
+                      name, packet_type);
+        err = EINVAL;
+        goto out;
     }
 
     if (!ipv6_addr_is_set(&tnl_cfg.ipv6_dst) && !tnl_cfg.ip_dst_flow) {
@@ -675,9 +707,12 @@ get_tunnel_config(const struct netdev *dev, struct smap *args)
         smap_add(args, "csum", "true");
     }
 
-    if (tnl_cfg.is_layer3 && (!strcmp("gre", type) ||
-        !strcmp("vxlan", type))) {
-        smap_add(args, "layer3", "true");
+    enum tunnel_layers layers = tunnel_supported_layers(type, &tnl_cfg);
+    if (tnl_cfg.pt_mode != default_pt_mode(layers)) {
+        smap_add(args, "packet_type",
+                 tnl_cfg.pt_mode == NETDEV_PT_LEGACY_L2 ? "legacy_l2"
+                 : tnl_cfg.pt_mode == NETDEV_PT_LEGACY_L3 ? "legacy_l3"
+                 : "ptap");
     }
 
     if (!tnl_cfg.dont_fragment) {
@@ -809,6 +844,15 @@ get_stats(const struct netdev *netdev, struct netdev_stats *stats)
     return 0;
 }
 
+static enum netdev_pt_mode
+get_pt_mode(const struct netdev *netdev)
+{
+    struct netdev_vport *dev = netdev_vport_cast(netdev);
+
+    return dev->tnl_cfg.pt_mode;
+}
+
+
 
 #ifdef __linux__
 static int
@@ -873,6 +917,7 @@ netdev_vport_get_ifindex(const struct netdev *netdev_)
                                                             \
     NULL,                       /* get_features */          \
     NULL,                       /* set_advertisements */    \
+    get_pt_mode,                                            \
                                                             \
     NULL,                       /* set_policing */          \
     NULL,                       /* get_qos_types */         \

diff --git a/lib/netdev-vport.h b/lib/netdev-vport.h
@@ -31,7 +31,6 @@ void netdev_vport_tunnel_register(void);
 void netdev_vport_patch_register(void);
 
 bool netdev_vport_is_patch(const struct netdev *);
-bool netdev_vport_is_layer3(const struct netdev *);
 
 char *netdev_vport_patch_peer(const struct netdev *netdev);
 

diff --git a/lib/netdev.c b/lib/netdev.c
@@ -727,6 +727,14 @@ netdev_set_tx_multiq(struct netdev *netdev, unsigned int n_txq)
     return error;
 }
 
+enum netdev_pt_mode
+netdev_get_pt_mode(const struct netdev *netdev)
+{
+    return (netdev->netdev_class->get_pt_mode
+            ? netdev->netdev_class->get_pt_mode(netdev)
+            : NETDEV_PT_LEGACY_L2);
+}
+
 /* Sends 'batch' on 'netdev'.  Returns 0 if successful (for every packet),
  * otherwise a positive errno value.  Returns EAGAIN without blocking if
  * at least one the packets cannot be queued immediately.  Returns EMSGSIZE