sfc: neighbour lookup for TC encap action offload

For each neighbour we're interested in, create a struct efx_neigh_binder
 object which has a list of all the encap_actions using it.  When we
 receive a neighbouring update (through the netevent notifier), find the
 corresponding efx_neigh_binder and update all its users.
Since the actual generation of encap headers is still only a stub, the
 resulting rules still get left on fallback actions.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Reviewed-by: Pieter Jansen van Vuuren <pieter.jansen-van-vuuren@amd.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/sfc/ef100_netdev.c

@@ -24,6 +24,7 @@
 #include "rx_common.h"
 #include "ef100_sriov.h"
 #include "tc_bindings.h"
+#include "tc_encap_actions.h"
 #include "efx_devlink.h"
 
 static void ef100_update_name(struct efx_nic *efx)
@@ -300,14 +301,38 @@ int ef100_netdev_event(struct notifier_block *this,
 {
 	struct efx_nic *efx = container_of(this, struct efx_nic, netdev_notifier);
 	struct net_device *net_dev = netdev_notifier_info_to_dev(ptr);
+	struct ef100_nic_data *nic_data = efx->nic_data;
+	int err;
 
 	if (efx->net_dev == net_dev &&
 	    (event == NETDEV_CHANGENAME || event == NETDEV_REGISTER))
 		ef100_update_name(efx);
 
+	if (!nic_data->grp_mae)
+		return NOTIFY_DONE;
+	err = efx_tc_netdev_event(efx, event, net_dev);
+	if (err & NOTIFY_STOP_MASK)
+		return err;
+
 	return NOTIFY_DONE;
 }
 
+static int ef100_netevent_event(struct notifier_block *this,
+				unsigned long event, void *ptr)
+{
+	struct efx_nic *efx = container_of(this, struct efx_nic, netevent_notifier);
+	struct ef100_nic_data *nic_data = efx->nic_data;
+	int err;
+
+	if (!nic_data->grp_mae)
+		return NOTIFY_DONE;
+	err = efx_tc_netevent_event(efx, event, ptr);
+	if (err & NOTIFY_STOP_MASK)
+		return err;
+
+	return NOTIFY_DONE;
+};
+
 static int ef100_register_netdev(struct efx_nic *efx)
 {
 	struct net_device *net_dev = efx->net_dev;
@@ -367,6 +392,7 @@ void ef100_remove_netdev(struct efx_probe_data *probe_data)
 	rtnl_unlock();
 
 	unregister_netdevice_notifier(&efx->netdev_notifier);
+	unregister_netevent_notifier(&efx->netevent_notifier);
 #if defined(CONFIG_SFC_SRIOV)
 	if (!efx->type->is_vf)
 		efx_ef100_pci_sriov_disable(efx, true);
@@ -487,6 +513,14 @@ int ef100_probe_netdev(struct efx_probe_data *probe_data)
 		goto fail;
 	}
 
+	efx->netevent_notifier.notifier_call = ef100_netevent_event;
+	rc = register_netevent_notifier(&efx->netevent_notifier);
+	if (rc) {
+		netif_err(efx, probe, efx->net_dev,
+			  "Failed to register netevent notifier, rc=%d\n", rc);
+		goto fail;
+	}
+
 	efx_probe_devlink_unlock(efx);
 	return rc;
 fail:

drivers/net/ethernet/sfc/net_driver.h

@@ -27,6 +27,7 @@
 #include <linux/mtd/mtd.h>
 #include <net/busy_poll.h>
 #include <net/xdp.h>
+#include <net/netevent.h>
 
 #include "enum.h"
 #include "bitfield.h"
@@ -996,6 +997,7 @@ struct efx_mae;
  * @xdp_rxq_info_failed: Have any of the rx queues failed to initialise their
  *      xdp_rxq_info structures?
  * @netdev_notifier: Netdevice notifier.
+ * @netevent_notifier: Netevent notifier (for neighbour updates).
  * @tc: state for TC offload (EF100).
  * @devlink: reference to devlink structure owned by this device
  * @dl_port: devlink port associated with the PF
@@ -1183,6 +1185,7 @@ struct efx_nic {
 	bool xdp_rxq_info_failed;
 
 	struct notifier_block netdev_notifier;
+	struct notifier_block netevent_notifier;
 	struct efx_tc_state *tc;
 
 	struct devlink *devlink;

drivers/net/ethernet/sfc/tc.c

@@ -34,8 +34,8 @@ enum efx_encap_type efx_tc_indr_netdev_type(struct net_device *net_dev)
  * May return NULL for the PF (us), or an error pointer for a device that
  * isn't supported as a TC offload endpoint
  */
-static struct efx_rep *efx_tc_flower_lookup_efv(struct efx_nic *efx,
-						struct net_device *dev)
+struct efx_rep *efx_tc_flower_lookup_efv(struct efx_nic *efx,
+					 struct net_device *dev)
 {
 	struct efx_rep *efv;
 
@@ -71,7 +71,7 @@ static s64 efx_tc_flower_internal_mport(struct efx_nic *efx, struct efx_rep *efv
 }
 
 /* Convert a driver-internal vport ID into an external device (wire or VF) */
-static s64 efx_tc_flower_external_mport(struct efx_nic *efx, struct efx_rep *efv)
+s64 efx_tc_flower_external_mport(struct efx_nic *efx, struct efx_rep *efv)
 {
 	u32 mport;
 
@@ -112,8 +112,10 @@ static void efx_tc_free_action_set(struct efx_nic *efx,
 	}
 	if (act->count)
 		efx_tc_flower_put_counter_index(efx, act->count);
-	if (act->encap_md)
+	if (act->encap_md) {
+		list_del(&act->encap_user);
 		efx_tc_flower_release_encap_md(efx, act->encap_md);
+	}
 	kfree(act);
 }
 
@@ -1115,6 +1117,7 @@ static int efx_tc_flower_replace(struct efx_nic *efx,
 					goto release;
 				}
 				act->encap_md = encap;
+				list_add_tail(&act->encap_user, &encap->users);
 				act->dest_mport = encap->dest_mport;
 				act->deliver = 1;
 				rc = efx_mae_alloc_action_set(efx, act);
@@ -1123,6 +1126,7 @@ static int efx_tc_flower_replace(struct efx_nic *efx,
 					goto release;
 				}
 				list_add_tail(&act->list, &rule->acts.list);
+				act->user = &rule->acts;
 				act = NULL;
 				if (fa->id == FLOW_ACTION_REDIRECT)
 					break; /* end of the line */

drivers/net/ethernet/sfc/tc.h

@@ -36,6 +36,8 @@ struct efx_tc_action_set {
 	__be16 vlan_proto[2]; /* Ethertypes for vlan_push */
 	struct efx_tc_counter_index *count;
 	struct efx_tc_encap_action *encap_md; /* entry in tc_encap_ht table */
+	struct list_head encap_user; /* entry on encap_md->users list */
+	struct efx_tc_action_set_list *user; /* Only populated if encap_md */
 	u32 dest_mport;
 	u32 fw_id; /* index of this entry in firmware actions table */
 	struct list_head list;
@@ -151,6 +153,7 @@ enum efx_tc_rule_prios {
  * @encap_ht: Hashtable of TC encap actions
  * @encap_match_ht: Hashtable of TC encap matches
  * @match_action_ht: Hashtable of TC match-action rules
+ * @neigh_ht: Hashtable of neighbour watches (&struct efx_neigh_binder)
  * @reps_mport_id: MAE port allocated for representor RX
  * @reps_filter_uc: VNIC filter for representor unicast RX (promisc)
  * @reps_filter_mc: VNIC filter for representor multicast RX (allmulti)
@@ -181,6 +184,7 @@ struct efx_tc_state {
 	struct rhashtable encap_ht;
 	struct rhashtable encap_match_ht;
 	struct rhashtable match_action_ht;
+	struct rhashtable neigh_ht;
 	u32 reps_mport_id, reps_mport_vport_id;
 	s32 reps_filter_uc, reps_filter_mc;
 	bool flush_counters;
@@ -201,6 +205,9 @@ struct efx_tc_state {
 struct efx_rep;
 
 enum efx_encap_type efx_tc_indr_netdev_type(struct net_device *net_dev);
+struct efx_rep *efx_tc_flower_lookup_efv(struct efx_nic *efx,
+					 struct net_device *dev);
+s64 efx_tc_flower_external_mport(struct efx_nic *efx, struct efx_rep *efv);
 int efx_tc_configure_default_rule_rep(struct efx_rep *efv);
 void efx_tc_deconfigure_default_rule(struct efx_nic *efx,
 				     struct efx_tc_flow_rule *rule);

drivers/net/ethernet/sfc/tc_bindings.c

@@ -10,6 +10,7 @@
 
 #include "tc_bindings.h"
 #include "tc.h"
+#include "tc_encap_actions.h"
 
 struct efx_tc_block_binding {
 	struct list_head list;
@@ -226,3 +227,15 @@ int efx_tc_setup(struct net_device *net_dev, enum tc_setup_type type,
 
 	return -EOPNOTSUPP;
 }
+
+int efx_tc_netdev_event(struct efx_nic *efx, unsigned long event,
+			struct net_device *net_dev)
+{
+	if (efx->type->is_vf)
+		return NOTIFY_DONE;
+
+	if (event == NETDEV_UNREGISTER)
+		efx_tc_unregister_egdev(efx, net_dev);
+
+	return NOTIFY_OK;
+}

drivers/net/ethernet/sfc/tc_bindings.h

@@ -26,4 +26,6 @@ int efx_tc_indr_setup_cb(struct net_device *net_dev, struct Qdisc *sch,
 			 void *cb_priv, enum tc_setup_type type,
 			 void *type_data, void *data,
 			 void (*cleanup)(struct flow_block_cb *block_cb));
+int efx_tc_netdev_event(struct efx_nic *efx, unsigned long event,
+			struct net_device *net_dev);
 #endif /* EFX_TC_BINDINGS_H */

drivers/net/ethernet/sfc/tc_encap_actions.h

@@ -15,6 +15,54 @@
 #include <linux/refcount.h>
 #include <net/tc_act/tc_tunnel_key.h>
 
+/**
+ * struct efx_neigh_binder - driver state for a neighbour entry
+ * @net: the network namespace in which this neigh resides
+ * @dst_ip: the IPv4 destination address resolved by this neigh
+ * @dst_ip6: the IPv6 destination address resolved by this neigh
+ * @ha: the hardware (Ethernet) address of the neighbour
+ * @n_valid: true if the neighbour is in NUD_VALID state
+ * @lock: protects @ha and @n_valid
+ * @ttl: Time To Live associated with the route used
+ * @dying: set when egdev is going away, to skip further updates
+ * @egdev: egress device from the route lookup.  Holds a reference
+ * @dev_tracker: reference tracker entry for @egdev
+ * @ns_tracker: reference tracker entry for @ns
+ * @ref: counts encap actions referencing this entry
+ * @used: jiffies of last time traffic hit any encap action using this.
+ *      When counter reads update this, a new neighbour event is sent to
+ *      indicate that the neighbour entry is still in use.
+ * @users: list of &struct efx_tc_encap_action
+ * @linkage: entry in efx->neigh_ht (keys are @net, @dst_ip, @dst_ip6).
+ * @work: processes neighbour state changes, updates the encap actions
+ * @efx: owning NIC instance.
+ *
+ * Associates a neighbour entry with the encap actions that are
+ * interested in it, allowing the latter to be updated when the
+ * neighbour details change.
+ * Whichever of @dst_ip and @dst_ip6 is not in use will be all-zeroes,
+ * this distinguishes IPv4 from IPv6 entries.
+ */
+struct efx_neigh_binder {
+	struct net *net;
+	__be32 dst_ip;
+	struct in6_addr dst_ip6;
+	char ha[ETH_ALEN];
+	bool n_valid;
+	rwlock_t lock;
+	u8 ttl;
+	bool dying;
+	struct net_device *egdev;
+	netdevice_tracker dev_tracker;
+	netns_tracker ns_tracker;
+	refcount_t ref;
+	unsigned long used;
+	struct list_head users;
+	struct rhash_head linkage;
+	struct work_struct work;
+	struct efx_nic *efx;
+};
+
 /* This limit is arbitrary; current hardware (SN1022) handles encap headers
  * of up to 126 bytes, but that limit is not enshrined in the MCDI protocol.
  */
@@ -24,7 +72,11 @@ struct efx_tc_encap_action {
 	struct ip_tunnel_key key; /* 52 bytes */
 	u32 dest_mport; /* is copied into struct efx_tc_action_set */
 	u8 encap_hdr_len;
+	bool n_valid;
 	u8 encap_hdr[EFX_TC_MAX_ENCAP_HDR];
+	struct efx_neigh_binder *neigh;
+	struct list_head list; /* entry on neigh->users list */
+	struct list_head users; /* action sets using this encap_md */
 	struct rhash_head linkage; /* efx->tc_encap_ht */
 	refcount_t ref;
 	u32 fw_id; /* index of this entry in firmware encap table */
@@ -44,4 +96,8 @@ struct efx_tc_encap_action *efx_tc_flower_create_encap_md(
 void efx_tc_flower_release_encap_md(struct efx_nic *efx,
 				    struct efx_tc_encap_action *encap);
 
+void efx_tc_unregister_egdev(struct efx_nic *efx, struct net_device *net_dev);
+int efx_tc_netevent_event(struct efx_nic *efx, unsigned long event,
+			  void *ptr);
+
 #endif /* EFX_TC_ENCAP_ACTIONS_H */