sfc: TC encap actions offload

index bb9ec1e761d3..24c67a163910 100644
@@ -1391,6 +1391,58 @@ void efx_tc_deconfigure_default_rule(struct efx_nic *efx,
 	rule->fw_id = MC_CMD_MAE_ACTION_RULE_INSERT_OUT_ACTION_RULE_ID_NULL;
 }
 
+static int efx_tc_configure_fallback_acts(struct efx_nic *efx, u32 eg_port,
+					  struct efx_tc_action_set_list *acts)
+{
+	struct efx_tc_action_set *act;
+	int rc;
+
+	act = kzalloc(sizeof(*act), GFP_KERNEL);
+	if (!act)
+		return -ENOMEM;
+	act->deliver = 1;
+	act->dest_mport = eg_port;
+	rc = efx_mae_alloc_action_set(efx, act);
+	if (rc)
+		goto fail1;
+	EFX_WARN_ON_PARANOID(!list_empty(&acts->list));
+	list_add_tail(&act->list, &acts->list);
+	rc = efx_mae_alloc_action_set_list(efx, acts);
+	if (rc)
+		goto fail2;
+	return 0;
+fail2:
+	list_del(&act->list);
+	efx_mae_free_action_set(efx, act->fw_id);
+fail1:
+	kfree(act);
+	return rc;
+}
+
+static int efx_tc_configure_fallback_acts_pf(struct efx_nic *efx)
+{
+	struct efx_tc_action_set_list *acts = &efx->tc->facts.pf;
+	u32 eg_port;
+
+	efx_mae_mport_uplink(efx, &eg_port);
+	return efx_tc_configure_fallback_acts(efx, eg_port, acts);
+}
+
+static int efx_tc_configure_fallback_acts_reps(struct efx_nic *efx)
+{
+	struct efx_tc_action_set_list *acts = &efx->tc->facts.reps;
+	u32 eg_port;
+
+	efx_mae_mport_mport(efx, efx->tc->reps_mport_id, &eg_port);
+	return efx_tc_configure_fallback_acts(efx, eg_port, acts);
+}
+
+static void efx_tc_deconfigure_fallback_acts(struct efx_nic *efx,
+					     struct efx_tc_action_set_list *acts)
+{
+	efx_tc_free_action_set_list(efx, acts, true);
+}
+
 static int efx_tc_configure_rep_mport(struct efx_nic *efx)
 {
 	u32 rep_mport_label;

@@ -1481,6 +1533,12 @@ int efx_init_tc(struct efx_nic *efx)
 	if (rc)
 		return rc;
 	rc = efx_tc_configure_rep_mport(efx);
+	if (rc)
+		return rc;
+	rc = efx_tc_configure_fallback_acts_pf(efx);
+	if (rc)
+		return rc;
+	rc = efx_tc_configure_fallback_acts_reps(efx);
 	if (rc)
 		return rc;
 	efx->tc->up = true;

@@ -1500,6 +1558,8 @@ void efx_fini_tc(struct efx_nic *efx)
 	efx_tc_deconfigure_rep_mport(efx);
 	efx_tc_deconfigure_default_rule(efx, &efx->tc->dflt.pf);
 	efx_tc_deconfigure_default_rule(efx, &efx->tc->dflt.wire);
+	efx_tc_deconfigure_fallback_acts(efx, &efx->tc->facts.pf);
+	efx_tc_deconfigure_fallback_acts(efx, &efx->tc->facts.reps);
 	efx->tc->up = false;
 }
 

@@ -1564,6 +1624,10 @@ int efx_init_struct_tc(struct efx_nic *efx)
 	efx->tc->dflt.pf.fw_id = MC_CMD_MAE_ACTION_RULE_INSERT_OUT_ACTION_RULE_ID_NULL;
 	INIT_LIST_HEAD(&efx->tc->dflt.wire.acts.list);
 	efx->tc->dflt.wire.fw_id = MC_CMD_MAE_ACTION_RULE_INSERT_OUT_ACTION_RULE_ID_NULL;
+	INIT_LIST_HEAD(&efx->tc->facts.pf.list);
+	efx->tc->facts.pf.fw_id = MC_CMD_MAE_ACTION_SET_ALLOC_OUT_ACTION_SET_ID_NULL;
+	INIT_LIST_HEAD(&efx->tc->facts.reps.list);
+	efx->tc->facts.reps.fw_id = MC_CMD_MAE_ACTION_SET_ALLOC_OUT_ACTION_SET_ID_NULL;
 	efx->extra_channel_type[EFX_EXTRA_CHANNEL_TC] = &efx_tc_channel_type;
 	return 0;
 fail_match_action_ht:

@@ -1589,6 +1653,10 @@ void efx_fini_struct_tc(struct efx_nic *efx)
 			     MC_CMD_MAE_ACTION_RULE_INSERT_OUT_ACTION_RULE_ID_NULL);
 	EFX_WARN_ON_PARANOID(efx->tc->dflt.wire.fw_id !=
 			     MC_CMD_MAE_ACTION_RULE_INSERT_OUT_ACTION_RULE_ID_NULL);
+	EFX_WARN_ON_PARANOID(efx->tc->facts.pf.fw_id !=
+			     MC_CMD_MAE_ACTION_SET_LIST_ALLOC_OUT_ACTION_SET_LIST_ID_NULL);
+	EFX_WARN_ON_PARANOID(efx->tc->facts.reps.fw_id !=
+			     MC_CMD_MAE_ACTION_SET_LIST_ALLOC_OUT_ACTION_SET_LIST_ID_NULL);
 	rhashtable_free_and_destroy(&efx->tc->match_action_ht, efx_tc_flow_free,
 				    efx);
 	rhashtable_free_and_destroy(&efx->tc->encap_match_ht,

index 24e9640c74e9..ae182553514d 100644
@@ -160,6 +160,11 @@ enum efx_tc_rule_prios {
  *	%EFX_TC_PRIO_DFLT.  Named by *ingress* port
  * @dflt.pf: rule for traffic ingressing from PF (egresses to wire)
  * @dflt.wire: rule for traffic ingressing from wire (egresses to PF)
+ * @facts: Fallback action-set-lists for unready rules.  Named by *egress* port
+ * @facts.pf: action-set-list for unready rules on PF netdev, hence applying to
+ *	traffic from wire, and egressing to PF
+ * @facts.reps: action-set-list for unready rules on representors, hence
+ *	applying to traffic from representees, and egressing to the reps mport
  * @up: have TC datastructures been set up?
  */
 struct efx_tc_state {

@@ -180,6 +185,10 @@ struct efx_tc_state {
 		struct efx_tc_flow_rule pf;
 		struct efx_tc_flow_rule wire;
 	} dflt;
+	struct {
+		struct efx_tc_action_set_list pf;
+		struct efx_tc_action_set_list reps;
+	} facts;
 	bool up;
 };
 

180 lines not on this page · raw message

index ae182553514d..5a8f701b05c5 100644
@@ -25,6 +25,8 @@ static inline bool efx_ipv6_addr_all_ones(struct in6_addr *addr)
 }
 #endif
 
+struct efx_tc_encap_action; /* see tc_encap_actions.h */
+
 struct efx_tc_action_set {
 	u16 vlan_push:2;
 	u16 vlan_pop:2;

@@ -33,6 +35,7 @@ struct efx_tc_action_set {
 	__be16 vlan_tci[2]; /* TCIs for vlan_push */
 	__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 */
 	u32 dest_mport;
 	u32 fw_id; /* index of this entry in firmware actions table */
 	struct list_head list;

@@ -127,6 +130,7 @@ struct efx_tc_flow_rule {
 	struct rhash_head linkage;
 	struct efx_tc_match match;
 	struct efx_tc_action_set_list acts;
+	struct efx_tc_action_set_list *fallback; /* what to use when unready? */
 	u32 fw_id;
 };
 

@@ -144,6 +148,7 @@ enum efx_tc_rule_prios {
  * @mutex: Used to serialise operations on TC hashtables
  * @counter_ht: Hashtable of TC counters (FW IDs and counter values)
  * @counter_id_ht: Hashtable mapping TC counter cookies to counters
+ * @encap_ht: Hashtable of TC encap actions
  * @encap_match_ht: Hashtable of TC encap matches
  * @match_action_ht: Hashtable of TC match-action rules
  * @reps_mport_id: MAE port allocated for representor RX

@@ -173,6 +178,7 @@ struct efx_tc_state {
 	struct mutex mutex;
 	struct rhashtable counter_ht;
 	struct rhashtable counter_id_ht;
+	struct rhashtable encap_ht;
 	struct rhashtable encap_match_ht;
 	struct rhashtable match_action_ht;
 	u32 reps_mport_id, reps_mport_vport_id;

@@ -194,6 +200,7 @@ struct efx_tc_state {
 
 struct efx_rep;
 
+enum efx_encap_type efx_tc_indr_netdev_type(struct net_device *net_dev);
 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);

126 lines not on this page · raw message

47 lines not on this page · raw message

index 37a4c6925ad4..4eef5d18817a 100644
@@ -1229,6 +1229,29 @@ int efx_mae_insert_rule(struct efx_nic *efx, const struct efx_tc_match *match,
 	return 0;
 }
 
+int efx_mae_update_rule(struct efx_nic *efx, u32 acts_id, u32 id)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_MAE_ACTION_RULE_UPDATE_IN_LEN);
+	MCDI_DECLARE_STRUCT_PTR(response);
+
+	BUILD_BUG_ON(MC_CMD_MAE_ACTION_RULE_UPDATE_OUT_LEN);
+	response = _MCDI_DWORD(inbuf, MAE_ACTION_RULE_UPDATE_IN_RESPONSE);
+
+	MCDI_SET_DWORD(inbuf, MAE_ACTION_RULE_UPDATE_IN_AR_ID, id);
+	if (efx_mae_asl_id(acts_id)) {
+		MCDI_STRUCT_SET_DWORD(response, MAE_ACTION_RULE_RESPONSE_ASL_ID, acts_id);
+		MCDI_STRUCT_SET_DWORD(response, MAE_ACTION_RULE_RESPONSE_AS_ID,
+				      MC_CMD_MAE_ACTION_SET_ALLOC_OUT_ACTION_SET_ID_NULL);
+	} else {
+		/* We only had one AS, so we didn't wrap it in an ASL */
+		MCDI_STRUCT_SET_DWORD(response, MAE_ACTION_RULE_RESPONSE_ASL_ID,
+				      MC_CMD_MAE_ACTION_SET_LIST_ALLOC_OUT_ACTION_SET_LIST_ID_NULL);
+		MCDI_STRUCT_SET_DWORD(response, MAE_ACTION_RULE_RESPONSE_AS_ID, acts_id);
+	}
+	return efx_mcdi_rpc(efx, MC_CMD_MAE_ACTION_RULE_UPDATE, inbuf, sizeof(inbuf),
+			    NULL, 0, NULL);
+}
+
 int efx_mae_delete_rule(struct efx_nic *efx, u32 id)
 {
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_MAE_ACTION_RULE_DELETE_OUT_LEN(1));

index 1cf8dfeb0c28..c542aab43ea1 100644
@@ -105,6 +105,7 @@ int efx_mae_unregister_encap_match(struct efx_nic *efx,
 
 int efx_mae_insert_rule(struct efx_nic *efx, const struct efx_tc_match *match,
 			u32 prio, u32 acts_id, u32 *id);
+int efx_mae_update_rule(struct efx_nic *efx, u32 acts_id, u32 id);
 int efx_mae_delete_rule(struct efx_nic *efx, u32 id);
 
 int efx_init_mae(struct efx_nic *efx);

index 4eef5d18817a..0cab508f2f9d 100644
@@ -15,6 +15,7 @@
 #include "mcdi.h"
 #include "mcdi_pcol.h"
 #include "mcdi_pcol_mae.h"
+#include "tc_encap_actions.h"
 
 int efx_mae_allocate_mport(struct efx_nic *efx, u32 *id, u32 *label)
 {

@@ -610,6 +611,87 @@ static int efx_mae_encap_type_to_mae_type(enum efx_encap_type type)
 	}
 }
 
+int efx_mae_allocate_encap_md(struct efx_nic *efx,
+			      struct efx_tc_encap_action *encap)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_MAE_ENCAP_HEADER_ALLOC_IN_LEN(EFX_TC_MAX_ENCAP_HDR));
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_MAE_ENCAP_HEADER_ALLOC_OUT_LEN);
+	size_t inlen, outlen;
+	int rc;
+
+	rc = efx_mae_encap_type_to_mae_type(encap->type);
+	if (rc < 0)
+		return rc;
+	MCDI_SET_DWORD(inbuf, MAE_ENCAP_HEADER_ALLOC_IN_ENCAP_TYPE, rc);
+	inlen = MC_CMD_MAE_ENCAP_HEADER_ALLOC_IN_LEN(encap->encap_hdr_len);
+	if (WARN_ON(inlen > sizeof(inbuf))) /* can't happen */
+		return -EINVAL;
+	memcpy(MCDI_PTR(inbuf, MAE_ENCAP_HEADER_ALLOC_IN_HDR_DATA),
+	       encap->encap_hdr,
+	       encap->encap_hdr_len);
+	rc = efx_mcdi_rpc(efx, MC_CMD_MAE_ENCAP_HEADER_ALLOC, inbuf,
+			  inlen, outbuf, sizeof(outbuf), &outlen);
+	if (rc)
+		return rc;
+	if (outlen < sizeof(outbuf))
+		return -EIO;
+	encap->fw_id = MCDI_DWORD(outbuf, MAE_ENCAP_HEADER_ALLOC_OUT_ENCAP_HEADER_ID);
+	return 0;
+}
+
+int efx_mae_update_encap_md(struct efx_nic *efx,
+			    struct efx_tc_encap_action *encap)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_MAE_ENCAP_HEADER_UPDATE_IN_LEN(EFX_TC_MAX_ENCAP_HDR));
+	size_t inlen;
+	int rc;
+
+	rc = efx_mae_encap_type_to_mae_type(encap->type);
+	if (rc < 0)
+		return rc;
+	MCDI_SET_DWORD(inbuf, MAE_ENCAP_HEADER_UPDATE_IN_ENCAP_TYPE, rc);
+	MCDI_SET_DWORD(inbuf, MAE_ENCAP_HEADER_UPDATE_IN_EH_ID,
+		       encap->fw_id);
+	inlen = MC_CMD_MAE_ENCAP_HEADER_UPDATE_IN_LEN(encap->encap_hdr_len);
+	if (WARN_ON(inlen > sizeof(inbuf))) /* can't happen */
+		return -EINVAL;
+	memcpy(MCDI_PTR(inbuf, MAE_ENCAP_HEADER_UPDATE_IN_HDR_DATA),
+	       encap->encap_hdr,
+	       encap->encap_hdr_len);
+
+	BUILD_BUG_ON(MC_CMD_MAE_ENCAP_HEADER_UPDATE_OUT_LEN != 0);
+	return efx_mcdi_rpc(efx, MC_CMD_MAE_ENCAP_HEADER_UPDATE, inbuf,
+			    inlen, NULL, 0, NULL);
+}
+
+int efx_mae_free_encap_md(struct efx_nic *efx,
+			  struct efx_tc_encap_action *encap)
+{
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_MAE_ENCAP_HEADER_FREE_OUT_LEN(1));
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_MAE_ENCAP_HEADER_FREE_IN_LEN(1));
+	size_t outlen;
+	int rc;
+
+	MCDI_SET_DWORD(inbuf, MAE_ENCAP_HEADER_FREE_IN_EH_ID, encap->fw_id);
+	rc = efx_mcdi_rpc(efx, MC_CMD_MAE_ENCAP_HEADER_FREE, inbuf,
+			  sizeof(inbuf), outbuf, sizeof(outbuf), &outlen);
+	if (rc)
+		return rc;
+	if (outlen < sizeof(outbuf))
+		return -EIO;
+	/* FW freed a different ID than we asked for, should also never happen.
+	 * Warn because it means we've now got a different idea to the FW of
+	 * what encap_mds exist, which could cause mayhem later.
+	 */
+	if (WARN_ON(MCDI_DWORD(outbuf, MAE_ENCAP_HEADER_FREE_OUT_FREED_EH_ID) != encap->fw_id))
+		return -EIO;
+	/* We're probably about to free @encap, but let's just make sure its
+	 * fw_id is blatted so that it won't look valid if it leaks out.
+	 */
+	encap->fw_id = MC_CMD_MAE_ENCAP_HEADER_ALLOC_OUT_ENCAP_HEADER_ID_NULL;
+	return 0;
+}
+
 int efx_mae_lookup_mport(struct efx_nic *efx, u32 vf_idx, u32 *id)
 {
 	struct ef100_nic_data *nic_data = efx->nic_data;

@@ -833,8 +915,12 @@ int efx_mae_alloc_action_set(struct efx_nic *efx, struct efx_tc_action_set *act)
 		MCDI_SET_WORD_BE(inbuf, MAE_ACTION_SET_ALLOC_IN_VLAN1_PROTO_BE,
 				 act->vlan_proto[1]);
 	}
-	MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_ENCAP_HEADER_ID,
-		       MC_CMD_MAE_ENCAP_HEADER_ALLOC_OUT_ENCAP_HEADER_ID_NULL);
+	if (act->encap_md)
+		MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_ENCAP_HEADER_ID,
+			       act->encap_md->fw_id);
+	else
+		MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_ENCAP_HEADER_ID,
+			       MC_CMD_MAE_ENCAP_HEADER_ALLOC_OUT_ENCAP_HEADER_ID_NULL);
 	if (act->deliver)
 		MCDI_SET_DWORD(inbuf, MAE_ACTION_SET_ALLOC_IN_DELIVER,
 			       act->dest_mport);

index c542aab43ea1..24abfe509690 100644
@@ -90,6 +90,13 @@ int efx_mae_check_encap_type_supported(struct efx_nic *efx,
 int efx_mae_allocate_counter(struct efx_nic *efx, struct efx_tc_counter *cnt);
 int efx_mae_free_counter(struct efx_nic *efx, struct efx_tc_counter *cnt);
 
+int efx_mae_allocate_encap_md(struct efx_nic *efx,
+			      struct efx_tc_encap_action *encap);
+int efx_mae_update_encap_md(struct efx_nic *efx,
+			    struct efx_tc_encap_action *encap);
+int efx_mae_free_encap_md(struct efx_nic *efx,
+			  struct efx_tc_encap_action *encap);
+
 int efx_mae_alloc_action_set(struct efx_nic *efx, struct efx_tc_action_set *act);
 int efx_mae_free_action_set(struct efx_nic *efx, u32 fw_id);
 

index 274f3a2562ad..7f7d560cb2b4 100644
@@ -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:

index fcd51d3992fa..a7a22b019794 100644
@@ -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;

index 4177feced3e6..77acdb60381e 100644
@@ -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 */

index 5a8f701b05c5..607429f8bb28 100644
@@ -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);

index c18d64519c2d..1b79c535c54e 100644
@@ -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;
+}

index c210bb09150e..095ddeb59eb3 100644
@@ -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 */

507 lines not on this page · raw message

73 lines not on this page · raw message

index c1bd7d468343..aac259528e73 100644
@@ -243,12 +243,183 @@ static void efx_release_neigh(struct efx_nic *efx,
 	efx_free_neigh(neigh);
 }
 
-static void efx_gen_encap_header(struct efx_tc_encap_action *encap)
+static void efx_gen_tun_header_eth(struct efx_tc_encap_action *encap, u16 proto)
 {
-	/* stub for now */
-	encap->n_valid = false;
-	memset(encap->encap_hdr, 0, sizeof(encap->encap_hdr));
-	encap->encap_hdr_len = ETH_HLEN;
+	struct efx_neigh_binder *neigh = encap->neigh;
+	struct ethhdr *eth;
+
+	encap->encap_hdr_len = sizeof(*eth);
+	eth = (struct ethhdr *)encap->encap_hdr;
+
+	if (encap->neigh->n_valid)
+		ether_addr_copy(eth->h_dest, neigh->ha);
+	else
+		eth_zero_addr(eth->h_dest);
+	ether_addr_copy(eth->h_source, neigh->egdev->dev_addr);
+	eth->h_proto = htons(proto);
+}
+
+static void efx_gen_tun_header_ipv4(struct efx_tc_encap_action *encap, u8 ipproto, u8 len)
+{
+	struct efx_neigh_binder *neigh = encap->neigh;
+	struct ip_tunnel_key *key = &encap->key;
+	struct iphdr *ip;
+
+	ip = (struct iphdr *)(encap->encap_hdr + encap->encap_hdr_len);
+	encap->encap_hdr_len += sizeof(*ip);
+
+	ip->daddr = key->u.ipv4.dst;
+	ip->saddr = key->u.ipv4.src;
+	ip->ttl = neigh->ttl;
+	ip->protocol = ipproto;
+	ip->version = 0x4;
+	ip->ihl = 0x5;
+	ip->tot_len = cpu_to_be16(ip->ihl * 4 + len);
+	ip_send_check(ip);
+}
+
+#ifdef CONFIG_IPV6
+static void efx_gen_tun_header_ipv6(struct efx_tc_encap_action *encap, u8 ipproto, u8 len)
+{
+	struct efx_neigh_binder *neigh = encap->neigh;
+	struct ip_tunnel_key *key = &encap->key;
+	struct ipv6hdr *ip;
+
+	ip = (struct ipv6hdr *)(encap->encap_hdr + encap->encap_hdr_len);
+	encap->encap_hdr_len += sizeof(*ip);
+
+	ip6_flow_hdr(ip, key->tos, key->label);
+	ip->daddr = key->u.ipv6.dst;
+	ip->saddr = key->u.ipv6.src;
+	ip->hop_limit = neigh->ttl;
+	ip->nexthdr = ipproto;
+	ip->version = 0x6;
+	ip->payload_len = cpu_to_be16(len);
+}
+#endif
+
+static void efx_gen_tun_header_udp(struct efx_tc_encap_action *encap, u8 len)
+{
+	struct ip_tunnel_key *key = &encap->key;
+	struct udphdr *udp;
+
+	udp = (struct udphdr *)(encap->encap_hdr + encap->encap_hdr_len);
+	encap->encap_hdr_len += sizeof(*udp);
+
+	udp->dest = key->tp_dst;
+	udp->len = cpu_to_be16(sizeof(*udp) + len);
+}
+
+static void efx_gen_tun_header_vxlan(struct efx_tc_encap_action *encap)
+{
+	struct ip_tunnel_key *key = &encap->key;
+	struct vxlanhdr *vxlan;
+
+	vxlan = (struct vxlanhdr *)(encap->encap_hdr + encap->encap_hdr_len);
+	encap->encap_hdr_len += sizeof(*vxlan);
+
+	vxlan->vx_flags = VXLAN_HF_VNI;
+	vxlan->vx_vni = vxlan_vni_field(tunnel_id_to_key32(key->tun_id));
+}
+
+static void efx_gen_tun_header_geneve(struct efx_tc_encap_action *encap)
+{
+	struct ip_tunnel_key *key = &encap->key;
+	struct genevehdr *geneve;
+	u32 vni;
+
+	geneve = (struct genevehdr *)(encap->encap_hdr + encap->encap_hdr_len);
+	encap->encap_hdr_len += sizeof(*geneve);
+
+	geneve->proto_type = htons(ETH_P_TEB);
+	/* convert tun_id to host-endian so we can use host arithmetic to
+	 * extract individual bytes.
+	 */
+	vni = ntohl(tunnel_id_to_key32(key->tun_id));
+	geneve->vni[0] = vni >> 16;
+	geneve->vni[1] = vni >> 8;
+	geneve->vni[2] = vni;
+}
+
+#define vxlan_header_l4_len	(sizeof(struct udphdr) + sizeof(struct vxlanhdr))
+#define vxlan4_header_len	(sizeof(struct ethhdr) + sizeof(struct iphdr) + vxlan_header_l4_len)
+static void efx_gen_vxlan_header_ipv4(struct efx_tc_encap_action *encap)
+{
+	BUILD_BUG_ON(sizeof(encap->encap_hdr) < vxlan4_header_len);
+	efx_gen_tun_header_eth(encap, ETH_P_IP);
+	efx_gen_tun_header_ipv4(encap, IPPROTO_UDP, vxlan_header_l4_len);
+	efx_gen_tun_header_udp(encap, sizeof(struct vxlanhdr));
+	efx_gen_tun_header_vxlan(encap);
+}
+
+#define geneve_header_l4_len	(sizeof(struct udphdr) + sizeof(struct genevehdr))
+#define geneve4_header_len	(sizeof(struct ethhdr) + sizeof(struct iphdr) + geneve_header_l4_len)
+static void efx_gen_geneve_header_ipv4(struct efx_tc_encap_action *encap)
+{
+	BUILD_BUG_ON(sizeof(encap->encap_hdr) < geneve4_header_len);
+	efx_gen_tun_header_eth(encap, ETH_P_IP);
+	efx_gen_tun_header_ipv4(encap, IPPROTO_UDP, geneve_header_l4_len);
+	efx_gen_tun_header_udp(encap, sizeof(struct genevehdr));
+	efx_gen_tun_header_geneve(encap);
+}
+
+#ifdef CONFIG_IPV6
+#define vxlan6_header_len	(sizeof(struct ethhdr) + sizeof(struct ipv6hdr) + vxlan_header_l4_len)
+static void efx_gen_vxlan_header_ipv6(struct efx_tc_encap_action *encap)
+{
+	BUILD_BUG_ON(sizeof(encap->encap_hdr) < vxlan6_header_len);
+	efx_gen_tun_header_eth(encap, ETH_P_IPV6);
+	efx_gen_tun_header_ipv6(encap, IPPROTO_UDP, vxlan_header_l4_len);
+	efx_gen_tun_header_udp(encap, sizeof(struct vxlanhdr));
+	efx_gen_tun_header_vxlan(encap);
+}
+
+#define geneve6_header_len	(sizeof(struct ethhdr) + sizeof(struct ipv6hdr) + geneve_header_l4_len)
+static void efx_gen_geneve_header_ipv6(struct efx_tc_encap_action *encap)
+{
+	BUILD_BUG_ON(sizeof(encap->encap_hdr) < geneve6_header_len);
+	efx_gen_tun_header_eth(encap, ETH_P_IPV6);
+	efx_gen_tun_header_ipv6(encap, IPPROTO_UDP, geneve_header_l4_len);
+	efx_gen_tun_header_udp(encap, sizeof(struct genevehdr));
+	efx_gen_tun_header_geneve(encap);
+}
+#endif
+
+static void efx_gen_encap_header(struct efx_nic *efx,
+				 struct efx_tc_encap_action *encap)
+{
+	encap->n_valid = encap->neigh->n_valid;
+
+	/* GCC stupidly thinks that only values explicitly listed in the enum
+	 * definition can _possibly_ be sensible case values, so without this
+	 * cast it complains about the IPv6 versions.
+	 */
+	switch ((int)encap->type) {
+	case EFX_ENCAP_TYPE_VXLAN:
+		efx_gen_vxlan_header_ipv4(encap);
+		break;
+	case EFX_ENCAP_TYPE_GENEVE:
+		efx_gen_geneve_header_ipv4(encap);
+		break;
+#ifdef CONFIG_IPV6
+	case EFX_ENCAP_TYPE_VXLAN | EFX_ENCAP_FLAG_IPV6:
+		efx_gen_vxlan_header_ipv6(encap);
+		break;
+	case EFX_ENCAP_TYPE_GENEVE | EFX_ENCAP_FLAG_IPV6:
+		efx_gen_geneve_header_ipv6(encap);
+		break;
+#endif
+	default:
+		/* unhandled encap type, can't happen */
+		if (net_ratelimit())
+			netif_err(efx, drv, efx->net_dev,
+				  "Bogus encap type %d, can't generate\n",
+				  encap->type);
+
+		/* Use fallback action. */
+		encap->n_valid = false;
+		break;
+	}
 }
 
 static void efx_tc_update_encap(struct efx_nic *efx,

@@ -282,14 +453,19 @@ static void efx_tc_update_encap(struct efx_nic *efx,
 		}
 	}
 
+	/* Make sure we don't leak arbitrary bytes on the wire;
+	 * set an all-0s ethernet header.  A successful call to
+	 * efx_gen_encap_header() will overwrite this.
+	 */
+	memset(encap->encap_hdr, 0, sizeof(encap->encap_hdr));
+	encap->encap_hdr_len = ETH_HLEN;
+
 	if (encap->neigh) {
 		read_lock_bh(&encap->neigh->lock);
-		efx_gen_encap_header(encap);
+		efx_gen_encap_header(efx, encap);
 		read_unlock_bh(&encap->neigh->lock);
 	} else {
 		encap->n_valid = false;
-		memset(encap->encap_hdr, 0, sizeof(encap->encap_hdr));
-		encap->encap_hdr_len = ETH_HLEN;
 	}
 
 	rc = efx_mae_update_encap_md(efx, encap);

@@ -486,7 +662,7 @@ struct efx_tc_encap_action *efx_tc_flower_create_encap_md(
 	}
 	encap->dest_mport = rc;
 	read_lock_bh(&encap->neigh->lock);
-	efx_gen_encap_header(encap);
+	efx_gen_encap_header(efx, encap);
 	read_unlock_bh(&encap->neigh->lock);
 
 	rc = efx_mae_allocate_encap_md(efx, encap);