net/mlx5e: Support multiple encapsulations for a TC flow

Currently a flow is associated with a single encap structure. The FW
extended destination features enables the driver to associate a flow
with multiple encap instances.

Change the encap id field from a flow scope to a per destination value
in the flow attributes struct. Use the encaps array to associate a flow
table entry with multiple encap entries.

Update the neigh logic to offload only if all encapsulations used in a
flow are connected, and un-offload upon the first one disconnected.

Note that the driver can now support up to two encap destinations.

Signed-off-by: Eli Britstein <elibr@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 58b83489a6d6af10d55229885a953a34773760ca..0921213561cb9893d9af5f5ed93f54d89017efe1 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -843,14 +843,15 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv,
 }
 
 static void mlx5e_detach_encap(struct mlx5e_priv *priv,
-                              struct mlx5e_tc_flow *flow);
+                              struct mlx5e_tc_flow *flow, int out_index);
 
 static int mlx5e_attach_encap(struct mlx5e_priv *priv,
                              struct ip_tunnel_info *tun_info,
                              struct net_device *mirred_dev,
                              struct net_device **encap_dev,
                              struct mlx5e_tc_flow *flow,
-                             struct netlink_ext_ack *extack);
+                             struct netlink_ext_ack *extack,
+                             int out_index);
 
 static struct mlx5_flow_handle *
 mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw,
@@ -955,18 +956,22 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
        }
 
        for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
+               int mirred_ifindex;
+
                if (!(attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
                        continue;
 
+               mirred_ifindex = attr->parse_attr->mirred_ifindex[out_index];
                out_dev = __dev_get_by_index(dev_net(priv->netdev),
-                                            attr->parse_attr->mirred_ifindex[0]);
-               encap_err = mlx5e_attach_encap(priv, &parse_attr->tun_info[0],
-                                              out_dev, &encap_dev, flow,
-                                              extack);
-               if (encap_err && encap_err != -EAGAIN) {
-                       err = encap_err;
+                                            mirred_ifindex);
+               err = mlx5e_attach_encap(priv,
+                                        &parse_attr->tun_info[out_index],
+                                        out_dev, &encap_dev, flow,
+                                        extack, out_index);
+               if (err && err != -EAGAIN)
                        goto err_attach_encap;
-               }
+               if (err == -EAGAIN)
+                       encap_err = err;
                out_priv = netdev_priv(encap_dev);
                rpriv = out_priv->ppriv;
                attr->dests[out_index].rep = rpriv->rep;
@@ -1022,10 +1027,8 @@ err_mod_hdr:
        mlx5_eswitch_del_vlan_action(esw, attr);
 err_add_vlan:
        for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++)
-               if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) {
-                       mlx5e_detach_encap(priv, flow);
-                       break;
-               }
+               if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)
+                       mlx5e_detach_encap(priv, flow, out_index);
 err_attach_encap:
 err_max_prio_chain:
        return err;
@@ -1049,10 +1052,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
        mlx5_eswitch_del_vlan_action(esw, attr);
 
        for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++)
-               if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) {
-                       mlx5e_detach_encap(priv, flow);
-                       break;
-               }
+               if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)
+                       mlx5e_detach_encap(priv, flow, out_index);
        kvfree(attr->parse_attr);
 
        if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
@@ -1087,11 +1088,30 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
        mlx5e_rep_queue_neigh_stats_work(priv);
 
        list_for_each_entry(efi, &e->flows, list) {
+               bool all_flow_encaps_valid = true;
+               int i;
+
                flow = container_of(efi, struct mlx5e_tc_flow, encaps[efi->index]);
                esw_attr = flow->esw_attr;
-               esw_attr->encap_id = e->encap_id;
                spec = &esw_attr->parse_attr->spec;
 
+               esw_attr->dests[efi->index].encap_id = e->encap_id;
+               esw_attr->dests[efi->index].flags |= MLX5_ESW_DEST_ENCAP_VALID;
+               /* Flow can be associated with multiple encap entries.
+                * Before offloading the flow verify that all of them have
+                * a valid neighbour.
+                */
+               for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) {
+                       if (!(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP))
+                               continue;
+                       if (!(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP_VALID)) {
+                               all_flow_encaps_valid = false;
+                               break;
+                       }
+               }
+               /* Do not offload flows with unresolved neighbors */
+               if (!all_flow_encaps_valid)
+                       continue;
                /* update from slow path rule to encap rule */
                rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, esw_attr);
                if (IS_ERR(rule)) {
@@ -1124,6 +1144,8 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 
                /* update from encap rule to slow path rule */
                rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec, &slow_attr);
+               /* mark the flow's encap dest as non-valid */
+               flow->esw_attr->dests[efi->index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID;
 
                if (IS_ERR(rule)) {
                        err = PTR_ERR(rule);
@@ -1207,11 +1229,11 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 }
 
 static void mlx5e_detach_encap(struct mlx5e_priv *priv,
-                              struct mlx5e_tc_flow *flow)
+                              struct mlx5e_tc_flow *flow, int out_index)
 {
-       struct list_head *next = flow->encaps[0].list.next;
+       struct list_head *next = flow->encaps[out_index].list.next;
 
-       list_del(&flow->encaps[0].list);
+       list_del(&flow->encaps[out_index].list);
        if (list_empty(next)) {
                struct mlx5e_encap_entry *e;
 
@@ -2324,7 +2346,8 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
                              struct net_device *mirred_dev,
                              struct net_device **encap_dev,
                              struct mlx5e_tc_flow *flow,
-                             struct netlink_ext_ack *extack)
+                             struct netlink_ext_ack *extack,
+                             int out_index)
 {
        struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
        unsigned short family = ip_tunnel_info_af(tun_info);
@@ -2371,13 +2394,15 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
        hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key);
 
 attach_flow:
-       list_add(&flow->encaps[0].list, &e->flows);
-       flow->encaps[0].index = 0;
+       list_add(&flow->encaps[out_index].list, &e->flows);
+       flow->encaps[out_index].index = out_index;
        *encap_dev = e->out_dev;
-       if (e->flags & MLX5_ENCAP_ENTRY_VALID)
-               attr->encap_id = e->encap_id;
-       else
+       if (e->flags & MLX5_ENCAP_ENTRY_VALID) {
+               attr->dests[out_index].encap_id = e->encap_id;
+               attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID;
+       } else {
                err = -EAGAIN;
+       }
 
        return err;
 
@@ -2516,8 +2541,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
                                attr->dests[attr->out_count].mdev = out_priv->mdev;
                                attr->out_count++;
                        } else if (encap) {
-                               parse_attr->mirred_ifindex[0] = out_dev->ifindex;
-                               parse_attr->tun_info[0] = *info;
+                               parse_attr->mirred_ifindex[attr->out_count] =
+                                       out_dev->ifindex;
+                               parse_attr->tun_info[attr->out_count] = *info;
+                               encap = false;
                                attr->parse_attr = parse_attr;
                                attr->dests[attr->out_count].flags |=
                                        MLX5_ESW_DEST_ENCAP;

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 39363d4662b3363481aec8b5aa629cd136f560d1..87c9dea9bccffb7fc5ec557de5f9e408127933bb 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -283,6 +283,7 @@ enum mlx5_flow_match_level {
 
 enum {
        MLX5_ESW_DEST_ENCAP         = BIT(0),
+       MLX5_ESW_DEST_ENCAP_VALID   = BIT(1),
 };
 
 struct mlx5_esw_flow_attr {
@@ -298,11 +299,11 @@ struct mlx5_esw_flow_attr {
        u8      vlan_prio[MLX5_FS_VLAN_DEPTH];
        u8      total_vlan;
        bool    vlan_handled;
-       u32     encap_id;
        struct {
                u32 flags;
                struct mlx5_eswitch_rep *rep;
                struct mlx5_core_dev *mdev;
+               u32 encap_id;
        } dests[MLX5_MAX_FLOW_FWD_VPORTS];
        u32     mod_hdr_id;
        u8      match_level;

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index b0652e44a68d580e5dfdac6a278a75595a025b36..bde1fb8c284b374d5854914c4f48a551bb0239a5 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -130,9 +130,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
                                                MLX5_FLOW_DEST_VPORT_VHCA_ID;
                                if (attr->dests[j].flags & MLX5_ESW_DEST_ENCAP) {
                                        flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
-                                       flow_act.reformat_id = attr->encap_id;
+                                       flow_act.reformat_id = attr->dests[j].encap_id;
                                        dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
-                                       dest[i].vport.reformat_id = attr->encap_id;
+                                       dest[i].vport.reformat_id =
+                                               attr->dests[j].encap_id;
                                }
                                i++;
                        }
@@ -228,7 +229,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
                        dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
                if (attr->dests[i].flags & MLX5_ESW_DEST_ENCAP) {
                        dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
-                       dest[i].vport.reformat_id = attr->encap_id;
+                       dest[i].vport.reformat_id = attr->dests[i].encap_id;
                }
        }
        dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;