Merge branch 'mlx5-sriov-vlan-push-pop'

Saeed Mahameed says:

====================
Mellanox 100G SRIOV offloads vlan push/pop

From Or Gerlitz:

This series further enhances the SRIOV TC offloads of mlx5 to handle
the TC vlan push and pop actions. This serves a common use-case in
virtualization systems where the virtual switch add (push) vlan tags
to packets sent from VMs and removes (pop) vlan tags before the packet
is received by the VM. We use the new E-Switch switchdev mode and the
TC vlan action to achieve that also in SW defined SRIOV environments by
offloading TC rules that contain this action along with forwarding
(TC mirred/redirect action) the packet.

In the first patch we add some helpers to access the TC vlan action info
by offloading drivers. The next five patches don't add any new functionality,
they do some refactoring and cleanups in the current code to be used next.

The seventh patch deals with supporting vlans by the mlx5 e-switch in switchdev
mode. The eighth patch does the vlan action offload from TC and the last patch
adds matching for vlans as typically required by TC flows that involve vlan
pop action.

The series was applied on top of commit 524605e "cxgb4: Convert to use simple_open()"
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -869,6 +869,7 @@ void mlx5e_nic_rep_unload(struct mlx5_eswitch *esw,
 int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv);
 void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv);
 int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr);
+void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 
 int mlx5e_create_direct_rqts(struct mlx5e_priv *priv);
 void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -446,6 +446,16 @@ static void mlx5e_rq_free_mpwqe_info(struct mlx5e_rq *rq)
 	kfree(rq->mpwqe.info);
 }
 
+static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
+{
+	struct mlx5_eswitch_rep *rep = (struct mlx5_eswitch_rep *)priv->ppriv;
+
+	if (rep && rep->vport != FDB_UPLINK_VPORT)
+		return true;
+
+	return false;
+}
+
 static int mlx5e_create_rq(struct mlx5e_channel *c,
 			   struct mlx5e_rq_param *param,
 			   struct mlx5e_rq *rq)
@@ -487,6 +497,11 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 
 	switch (priv->params.rq_wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		if (mlx5e_is_vf_vport_rep(priv)) {
+			err = -EINVAL;
+			goto err_rq_wq_destroy;
+		}
+
 		rq->handle_rx_cqe = mlx5e_handle_rx_cqe_mpwrq;
 		rq->alloc_wqe = mlx5e_alloc_rx_mpwqe;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
@@ -512,7 +527,11 @@ static int mlx5e_create_rq(struct mlx5e_channel *c,
 			goto err_rq_wq_destroy;
 		}
 
-		rq->handle_rx_cqe = mlx5e_handle_rx_cqe;
+		if (mlx5e_is_vf_vport_rep(priv))
+			rq->handle_rx_cqe = mlx5e_handle_rx_cqe_rep;
+		else
+			rq->handle_rx_cqe = mlx5e_handle_rx_cqe;
+
 		rq->alloc_wqe = mlx5e_alloc_rx_wqe;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_wqe;
 
@@ -3726,9 +3745,9 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 		mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id);
 		rep.load = mlx5e_nic_rep_load;
 		rep.unload = mlx5e_nic_rep_unload;
-		rep.vport = 0;
+		rep.vport = FDB_UPLINK_VPORT;
 		rep.priv_data = priv;
-		mlx5_eswitch_register_vport_rep(esw, &rep);
+		mlx5_eswitch_register_vport_rep(esw, 0, &rep);
 	}
 }
 
@@ -3867,7 +3886,7 @@ static void mlx5e_register_vport_rep(struct mlx5_core_dev *mdev)
 		rep.unload = mlx5e_vport_rep_unload;
 		rep.vport = vport;
 		ether_addr_copy(rep.hw_id, mac);
-		mlx5_eswitch_register_vport_rep(esw, &rep);
+		mlx5_eswitch_register_vport_rep(esw, vport, &rep);
 	}
 }
 

drivers/net/ethernet/mellanox/mlx5/core/en_rx.c

@@ -36,6 +36,7 @@
 #include <net/busy_poll.h>
 #include "en.h"
 #include "en_tc.h"
+#include "eswitch.h"
 
 static inline bool mlx5e_rx_hw_stamp(struct mlx5e_tstamp *tstamp)
 {
@@ -629,7 +630,6 @@ static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
 	rq->stats.packets++;
 	rq->stats.bytes += cqe_bcnt;
 	mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb);
-	napi_gro_receive(rq->cq.napi, skb);
 }
 
 static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_sq *sq)
@@ -733,20 +733,15 @@ static inline bool mlx5e_xdp_handle(struct mlx5e_rq *rq,
 	}
 }
 
-void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+static inline
+struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
+			     u16 wqe_counter, u32 cqe_bcnt)
 {
 	struct bpf_prog *xdp_prog = READ_ONCE(rq->xdp_prog);
 	struct mlx5e_dma_info *di;
-	struct mlx5e_rx_wqe *wqe;
-	__be16 wqe_counter_be;
 	struct sk_buff *skb;
-	u16 wqe_counter;
 	void *va, *data;
-	u32 cqe_bcnt;
 
-	wqe_counter_be = cqe->wqe_counter;
-	wqe_counter    = be16_to_cpu(wqe_counter_be);
-	wqe            = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter);
 	di             = &rq->dma_info[wqe_counter];
 	va             = page_address(di->page);
 	data           = va + MLX5_RX_HEADROOM;
@@ -757,22 +752,21 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 				      rq->buff.wqe_sz,
 				      DMA_FROM_DEVICE);
 	prefetch(data);
-	cqe_bcnt = be32_to_cpu(cqe->byte_cnt);
 
 	if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
 		rq->stats.wqe_err++;
 		mlx5e_page_release(rq, di, true);
-		goto wq_ll_pop;
+		return NULL;
 	}
 
 	if (mlx5e_xdp_handle(rq, xdp_prog, di, data, cqe_bcnt))
-		goto wq_ll_pop; /* page/packet was consumed by XDP */
+		return NULL; /* page/packet was consumed by XDP */
 
 	skb = build_skb(va, RQ_PAGE_SIZE(rq));
 	if (unlikely(!skb)) {
 		rq->stats.buff_alloc_err++;
 		mlx5e_page_release(rq, di, true);
-		goto wq_ll_pop;
+		return NULL;
 	}
 
 	/* queue up for recycling ..*/
@@ -782,7 +776,60 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	skb_reserve(skb, MLX5_RX_HEADROOM);
 	skb_put(skb, cqe_bcnt);
 
+	return skb;
+}
+
+void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+{
+	struct mlx5e_rx_wqe *wqe;
+	__be16 wqe_counter_be;
+	struct sk_buff *skb;
+	u16 wqe_counter;
+	u32 cqe_bcnt;
+
+	wqe_counter_be = cqe->wqe_counter;
+	wqe_counter    = be16_to_cpu(wqe_counter_be);
+	wqe            = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter);
+	cqe_bcnt       = be32_to_cpu(cqe->byte_cnt);
+
+	skb = skb_from_cqe(rq, cqe, wqe_counter, cqe_bcnt);
+	if (!skb)
+		goto wq_ll_pop;
+
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	napi_gro_receive(rq->cq.napi, skb);
+
+wq_ll_pop:
+	mlx5_wq_ll_pop(&rq->wq, wqe_counter_be,
+		       &wqe->next.next_wqe_index);
+}
+
+void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+{
+	struct net_device *netdev = rq->netdev;
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_eswitch_rep *rep = priv->ppriv;
+	struct mlx5e_rx_wqe *wqe;
+	struct sk_buff *skb;
+	__be16 wqe_counter_be;
+	u16 wqe_counter;
+	u32 cqe_bcnt;
+
+	wqe_counter_be = cqe->wqe_counter;
+	wqe_counter    = be16_to_cpu(wqe_counter_be);
+	wqe            = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter);
+	cqe_bcnt       = be32_to_cpu(cqe->byte_cnt);
+
+	skb = skb_from_cqe(rq, cqe, wqe_counter, cqe_bcnt);
+	if (!skb)
+		goto wq_ll_pop;
+
+	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+
+	if (rep->vlan && skb_vlan_tag_present(skb))
+		skb_vlan_pop(skb);
+
+	napi_gro_receive(rq->cq.napi, skb);
 
 wq_ll_pop:
 	mlx5_wq_ll_pop(&rq->wq, wqe_counter_be,
@@ -861,6 +908,7 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 
 	mlx5e_mpwqe_fill_rx_skb(rq, cqe, wi, cqe_bcnt, skb);
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	napi_gro_receive(rq->cq.napi, skb);
 
 mpwrq_cqe_out:
 	if (likely(wi->consumed_strides < rq->mpwqe_num_strides))