ice: add VF representors one by one

Implement adding representors one by one. Always set switchdev
environment when first representor is being added and clear environment
when last one is being removed.

Basic switchdev configuration remains the same. Code related to creating
and configuring representor was changed.

Instead of setting whole representors in one function handle only one
representor in setup function. The same with removing representors.

Stop representors when new one is being added or removed. Stop means,
disabling napi, stopping traffic and removing slow path rule. It is
needed because ::q_id will change after remapping, so each representor
will need new rule.

When representor are stopped rebuild control plane VSI with one more or
one less queue. One more if new representor is being added, one less if
representor is being removed.

Bridge port is removed during unregister_netdev() call on PR, so there
is no need to call it from driver side.

After that do remap new queues to correct vector. At the end start all
representors (napi enable, start queues, add slow path rule).

Reviewed-by: Piotr Raczynski <piotr.raczynski@intel.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>

1 files changed, 196 insertions, 155 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index db70a62429e3..de5744aa5c2a 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -11,6 +11,24 @@
 #include "ice_tc_lib.h"
 
 /**
+ * ice_eswitch_del_sp_rules - delete adv rules added on PRs
+ * @pf: pointer to the PF struct
+ *
+ * Delete all advanced rules that were used to forward packets with the
+ * device's VSI index to the corresponding eswitch ctrl VSI queue.
+ */
+static void ice_eswitch_del_sp_rules(struct ice_pf *pf)
+{
+	struct ice_repr *repr;
+	unsigned long id;
+
+	xa_for_each(&pf->eswitch.reprs, id, repr) {
+		if (repr->sp_rule.rid)
+			ice_rem_adv_rule_by_id(&pf->hw, &repr->sp_rule);
+	}
+}
+
+/**
  * ice_eswitch_add_sp_rule - add adv rule with device's VSI index
  * @pf: pointer to PF struct
  * @repr: pointer to the repr struct
@@ -18,8 +36,7 @@
  * This function adds advanced rule that forwards packets with
  * device's VSI index to the corresponding eswitch ctrl VSI queue.
  */
-static int
-ice_eswitch_add_sp_rule(struct ice_pf *pf, struct ice_repr *repr)
+static int ice_eswitch_add_sp_rule(struct ice_pf *pf, struct ice_repr *repr)
 {
 	struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi;
 	struct ice_adv_rule_info rule_info = { 0 };
@@ -54,17 +71,22 @@ ice_eswitch_add_sp_rule(struct ice_pf *pf, struct ice_repr *repr)
 	return err;
 }
 
-/**
- * ice_eswitch_del_sp_rule - delete adv rule with device's VSI index
- * @pf: pointer to the PF struct
- * @repr: pointer to the repr struct
- *
- * Delete the advanced rule that was used to forward packets with the device's
- * VSI index to the corresponding eswitch ctrl VSI queue.
- */
-static void ice_eswitch_del_sp_rule(struct ice_pf *pf, struct ice_repr *repr)
+static int
+ice_eswitch_add_sp_rules(struct ice_pf *pf)
 {
-	ice_rem_adv_rule_by_id(&pf->hw, &repr->sp_rule);
+	struct ice_repr *repr;
+	unsigned long id;
+	int err;
+
+	xa_for_each(&pf->eswitch.reprs, id, repr) {
+		err = ice_eswitch_add_sp_rule(pf, repr);
+		if (err) {
+			ice_eswitch_del_sp_rules(pf);
+			return err;
+		}
+	}
+
+	return 0;
 }
 
 /**
@@ -131,7 +153,7 @@ err_def_rx:
 
 /**
  * ice_eswitch_remap_rings_to_vectors - reconfigure rings of eswitch ctrl VSI
- * @pf: pointer to PF struct
+ * @eswitch: pointer to eswitch struct
  *
  * In eswitch number of allocated Tx/Rx rings is equal.
  *
@@ -140,9 +162,9 @@ err_def_rx:
  * will have dedicated 1 Tx/Rx ring pair, so number of rings pair is equal to
  * number of VFs.
  */
-static void ice_eswitch_remap_rings_to_vectors(struct ice_pf *pf)
+static void ice_eswitch_remap_rings_to_vectors(struct ice_eswitch *eswitch)
 {
-	struct ice_vsi *vsi = pf->eswitch.control_vsi;
+	struct ice_vsi *vsi = eswitch->control_vsi;
 	unsigned long repr_id = 0;
 	int q_id;
 
@@ -152,7 +174,7 @@ static void ice_eswitch_remap_rings_to_vectors(struct ice_pf *pf)
 		struct ice_rx_ring *rx_ring;
 		struct ice_repr *repr;
 
-		repr = xa_find(&pf->eswitch.reprs, &repr_id, U32_MAX,
+		repr = xa_find(&eswitch->reprs, &repr_id, U32_MAX,
 			       XA_PRESENT);
 		if (WARN_ON(!repr))
 			break;
@@ -185,100 +207,70 @@ static void ice_eswitch_remap_rings_to_vectors(struct ice_pf *pf)
 }
 
 /**
- * ice_eswitch_release_reprs - clear PR VSIs configuration
+ * ice_eswitch_release_repr - clear PR VSI configuration
  * @pf: poiner to PF struct
+ * @repr: pointer to PR
  */
 static void
-ice_eswitch_release_reprs(struct ice_pf *pf)
+ice_eswitch_release_repr(struct ice_pf *pf, struct ice_repr *repr)
 {
-	struct ice_repr *repr;
-	unsigned long id;
+	struct ice_vsi *vsi = repr->src_vsi;
 
-	xa_for_each(&pf->eswitch.reprs, id, repr) {
-		struct ice_vsi *vsi = repr->src_vsi;
-
-		/* Skip representors that aren't configured */
-		if (!repr->dst)
-			continue;
+	/* Skip representors that aren't configured */
+	if (!repr->dst)
+		return;
 
-		ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof);
-		metadata_dst_free(repr->dst);
-		repr->dst = NULL;
-		ice_eswitch_del_sp_rule(pf, repr);
-		ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac,
-					       ICE_FWD_TO_VSI);
+	ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof);
+	metadata_dst_free(repr->dst);
+	repr->dst = NULL;
+	ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac,
+				       ICE_FWD_TO_VSI);
 
-		netif_napi_del(&repr->q_vector->napi);
-	}
+	netif_napi_del(&repr->q_vector->napi);
 }
 
 /**
- * ice_eswitch_setup_reprs - configure port reprs to run in switchdev mode
+ * ice_eswitch_setup_repr - configure PR to run in switchdev mode
  * @pf: pointer to PF struct
+ * @repr: pointer to PR struct
  */
-static int ice_eswitch_setup_reprs(struct ice_pf *pf)
+static int ice_eswitch_setup_repr(struct ice_pf *pf, struct ice_repr *repr)
 {
 	struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi;
-	struct ice_repr *repr;
-	unsigned long id;
-
-	xa_for_each(&pf->eswitch.reprs, id, repr) {
-		struct ice_vsi *vsi = repr->src_vsi;
-
-		ice_remove_vsi_fltr(&pf->hw, vsi->idx);
-		repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX,
-					       GFP_KERNEL);
-		if (!repr->dst) {
-			ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac,
-						       ICE_FWD_TO_VSI);
-			goto err;
-		}
+	struct ice_vsi *vsi = repr->src_vsi;
+	struct metadata_dst *dst;
 
-		if (ice_eswitch_add_sp_rule(pf, repr)) {
-			ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac,
-						       ICE_FWD_TO_VSI);
-			goto err;
-		}
+	ice_remove_vsi_fltr(&pf->hw, vsi->idx);
+	repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX,
+				       GFP_KERNEL);
+	if (!repr->dst)
+		goto err_add_mac_fltr;
 
-		if (ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof)) {
-			ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac,
-						       ICE_FWD_TO_VSI);
-			ice_eswitch_del_sp_rule(pf, repr);
-			metadata_dst_free(repr->dst);
-			repr->dst = NULL;
-			goto err;
-		}
+	if (ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof))
+		goto err_dst_free;
 
-		if (ice_vsi_add_vlan_zero(vsi)) {
-			ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac,
-						       ICE_FWD_TO_VSI);
-			ice_eswitch_del_sp_rule(pf, repr);
-			metadata_dst_free(repr->dst);
-			repr->dst = NULL;
-			ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof);
-			goto err;
-		}
+	if (ice_vsi_add_vlan_zero(vsi))
+		goto err_update_security;
 
-		netif_napi_add(repr->netdev, &repr->q_vector->napi,
-			       ice_napi_poll);
+	netif_napi_add(repr->netdev, &repr->q_vector->napi,
+		       ice_napi_poll);
 
-		netif_keep_dst(repr->netdev);
-	}
+	netif_keep_dst(repr->netdev);
 
-	xa_for_each(&pf->eswitch.reprs, id, repr) {
-		struct ice_vsi *vsi = repr->src_vsi;
-		struct metadata_dst *dst;
-
-		dst = repr->dst;
-		dst->u.port_info.port_id = vsi->vsi_num;
-		dst->u.port_info.lower_dev = repr->netdev;
-		ice_repr_set_traffic_vsi(repr, ctrl_vsi);
-	}
+	dst = repr->dst;
+	dst->u.port_info.port_id = vsi->vsi_num;
+	dst->u.port_info.lower_dev = repr->netdev;
+	ice_repr_set_traffic_vsi(repr, ctrl_vsi);
 
 	return 0;
 
-err:
-	ice_eswitch_release_reprs(pf);
+err_update_security:
+	ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof);
+err_dst_free:
+	metadata_dst_free(repr->dst);
+	repr->dst = NULL;
+err_add_mac_fltr:
+	ice_fltr_add_mac_and_broadcast(vsi, repr->parent_mac, ICE_FWD_TO_VSI);
 
 	return -ENODEV;
 }
@@ -481,31 +473,14 @@ static int ice_eswitch_enable_switchdev(struct ice_pf *pf)
 	if (ice_eswitch_setup_env(pf))
 		goto err_vsi;
 
-	if (ice_repr_add_for_all_vfs(pf))
-		goto err_repr_add;
-
-	if (ice_eswitch_setup_reprs(pf))
-		goto err_setup_reprs;
-
-	ice_eswitch_remap_rings_to_vectors(pf);
-
-	if (ice_vsi_open(ctrl_vsi))
-		goto err_vsi_open;
-
 	if (ice_eswitch_br_offloads_init(pf))
 		goto err_br_offloads;
 
-	ice_eswitch_napi_enable(&pf->eswitch.reprs);
+	pf->eswitch.is_running = true;
 
 	return 0;
 
 err_br_offloads:
-	ice_vsi_close(ctrl_vsi);
-err_vsi_open:
-	ice_eswitch_release_reprs(pf);
-err_setup_reprs:
-	ice_repr_rem_from_all_vfs(pf);
-err_repr_add:
 	ice_eswitch_release_env(pf);
 err_vsi:
 	ice_vsi_release(ctrl_vsi);
@@ -519,22 +494,12 @@ err_vsi:
 static void ice_eswitch_disable_switchdev(struct ice_pf *pf)
 {
 	struct ice_vsi *ctrl_vsi = pf->eswitch.control_vsi;
-	struct devlink *devlink = priv_to_devlink(pf);
 
-	ice_eswitch_napi_disable(&pf->eswitch.reprs);
 	ice_eswitch_br_offloads_deinit(pf);
 	ice_eswitch_release_env(pf);
-	ice_eswitch_release_reprs(pf);
 	ice_vsi_release(ctrl_vsi);
-	ice_repr_rem_from_all_vfs(pf);
-
-	/* since all port representors are destroyed, there is
-	 * no point in keeping the nodes
-	 */
-	ice_devlink_rate_clear_tx_topology(ice_get_main_vsi(pf));
-	devl_lock(devlink);
-	devl_rate_nodes_destroy(devlink);
-	devl_unlock(devlink);
+
+	pf->eswitch.is_running = false;
 }
 
 /**
@@ -614,39 +579,6 @@ bool ice_is_eswitch_mode_switchdev(struct ice_pf *pf)
 }
 
 /**
- * ice_eswitch_release - cleanup eswitch
- * @pf: pointer to PF structure
- */
-void ice_eswitch_release(struct ice_pf *pf)
-{
-	if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY)
-		return;
-
-	ice_eswitch_disable_switchdev(pf);
-	pf->eswitch.is_running = false;
-}
-
-/**
- * ice_eswitch_configure - configure eswitch
- * @pf: pointer to PF structure
- */
-int ice_eswitch_configure(struct ice_pf *pf)
-{
-	int status;
-
-	if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY ||
-	    pf->eswitch.is_running)
-		return 0;
-
-	status = ice_eswitch_enable_switchdev(pf);
-	if (status)
-		return status;
-
-	pf->eswitch.is_running = true;
-	return 0;
-}
-
-/**
  * ice_eswitch_start_all_tx_queues - start Tx queues of all port representors
  * @pf: pointer to PF structure
  */
@@ -678,6 +610,20 @@ void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf)
 		ice_repr_stop_tx_queues(repr);
 }
 
+static void ice_eswitch_stop_reprs(struct ice_pf *pf)
+{
+	ice_eswitch_del_sp_rules(pf);
+	ice_eswitch_stop_all_tx_queues(pf);
+	ice_eswitch_napi_disable(&pf->eswitch.reprs);
+}
+
+static void ice_eswitch_start_reprs(struct ice_pf *pf)
+{
+	ice_eswitch_napi_enable(&pf->eswitch.reprs);
+	ice_eswitch_start_all_tx_queues(pf);
+	ice_eswitch_add_sp_rules(pf);
+}
+
 /**
  * ice_eswitch_rebuild - rebuild eswitch
  * @pf: pointer to PF structure
@@ -694,11 +640,7 @@ int ice_eswitch_rebuild(struct ice_pf *pf)
 	if (status)
 		return status;
 
-	status = ice_eswitch_setup_reprs(pf);
-	if (status)
-		return status;
-
-	ice_eswitch_remap_rings_to_vectors(pf);
+	ice_eswitch_remap_rings_to_vectors(&pf->eswitch);
 
 	ice_replay_tc_fltrs(pf);
 
@@ -711,3 +653,102 @@ int ice_eswitch_rebuild(struct ice_pf *pf)
 
 	return 0;
 }
+
+static void
+ice_eswitch_cp_change_queues(struct ice_eswitch *eswitch, int change)
+{
+	struct ice_vsi *cp = eswitch->control_vsi;
+
+	ice_vsi_close(cp);
+
+	cp->req_txq = cp->alloc_txq + change;
+	cp->req_rxq = cp->alloc_rxq + change;
+	ice_vsi_rebuild(cp, ICE_VSI_FLAG_NO_INIT);
+	ice_eswitch_remap_rings_to_vectors(eswitch);
+
+	ice_vsi_open(cp);
+}
+
+int
+ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf)
+{
+	struct ice_repr *repr;
+	int change = 1;
+	int err;
+
+	if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY)
+		return 0;
+
+	if (xa_empty(&pf->eswitch.reprs)) {
+		err = ice_eswitch_enable_switchdev(pf);
+		if (err)
+			return err;
+		/* Control plane VSI is created with 1 queue as default */
+		change = 0;
+	}
+
+	ice_eswitch_stop_reprs(pf);
+
+	repr = ice_repr_add_vf(vf);
+	if (IS_ERR(repr))
+		goto err_create_repr;
+
+	err = ice_eswitch_setup_repr(pf, repr);
+	if (err)
+		goto err_setup_repr;
+
+	err = xa_alloc(&pf->eswitch.reprs, &repr->id, repr,
+		       XA_LIMIT(1, INT_MAX), GFP_KERNEL);
+	if (err)
+		goto err_xa_alloc;
+
+	vf->repr_id = repr->id;
+
+	ice_eswitch_cp_change_queues(&pf->eswitch, change);
+	ice_eswitch_start_reprs(pf);
+
+	return 0;
+
+err_xa_alloc:
+	ice_eswitch_release_repr(pf, repr);
+err_setup_repr:
+	ice_repr_rem_vf(repr);
+err_create_repr:
+	if (xa_empty(&pf->eswitch.reprs))
+		ice_eswitch_disable_switchdev(pf);
+	ice_eswitch_start_reprs(pf);
+
+	return err;
+}
+
+void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf)
+{
+	struct ice_repr *repr = xa_load(&pf->eswitch.reprs, vf->repr_id);
+	struct devlink *devlink = priv_to_devlink(pf);
+
+	if (!repr)
+		return;
+
+	ice_eswitch_stop_reprs(pf);
+	xa_erase(&pf->eswitch.reprs, repr->id);
+
+	if (xa_empty(&pf->eswitch.reprs))
+		ice_eswitch_disable_switchdev(pf);
+	else
+		ice_eswitch_cp_change_queues(&pf->eswitch, -1);
+
+	ice_eswitch_release_repr(pf, repr);
+	ice_repr_rem_vf(repr);
+
+	if (xa_empty(&pf->eswitch.reprs)) {
+		/* since all port representors are destroyed, there is
+		 * no point in keeping the nodes
+		 */
+		ice_devlink_rate_clear_tx_topology(ice_get_main_vsi(pf));
+		devl_lock(devlink);
+		devl_rate_nodes_destroy(devlink);
+		devl_unlock(devlink);
+	} else {
+		ice_eswitch_start_reprs(pf);
+	}
+}