Merge branch '10GbE' of git://git.kernel.org/pub/scm/linux/kernel/git…

…/jkirsher/next-queue

Jeff Kirsher says:

====================
L2 Fwd Offload & 10GbE Intel Driver Updates 2018-07-09

This patch series is meant to allow support for the L2 forward offload, aka
MACVLAN offload without the need for using ndo_select_queue.

The existing solution currently requires that we use ndo_select_queue in
the transmit path if we want to associate specific Tx queues with a given
MACVLAN interface. In order to get away from this we need to repurpose the
tc_to_txq array and XPS pointer for the MACVLAN interface and use those as
a means of accessing the queues on the lower device. As a result we cannot
offload a device that is configured as multiqueue, however it doesn't
really make sense to configure a macvlan interfaced as being multiqueue
anyway since it doesn't really have a qdisc of its own in the first place.

The big changes in this set are:
  Allow lower device to update tc_to_txq and XPS map of offloaded MACVLAN
  Disable XPS for single queue devices
  Replace accel_priv with sb_dev in ndo_select_queue
  Add sb_dev parameter to fallback function for ndo_select_queue
  Consolidated ndo_select_queue functions that appeared to be duplicates
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/infiniband/hw/hfi1/vnic_main.c

@@ -423,7 +423,7 @@ static netdev_tx_t hfi1_netdev_start_xmit(struct sk_buff *skb,
 
 static u16 hfi1_vnic_select_queue(struct net_device *netdev,
 				  struct sk_buff *skb,
-				  void *accel_priv,
+				  struct net_device *sb_dev,
 				  select_queue_fallback_t fallback)
 {
 	struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);

drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c

@@ -95,7 +95,7 @@ static netdev_tx_t opa_netdev_start_xmit(struct sk_buff *skb,
 }
 
 static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb,
-				 void *accel_priv,
+				 struct net_device *sb_dev,
 				 select_queue_fallback_t fallback)
 {
 	struct opa_vnic_adapter *adapter = opa_vnic_priv(netdev);
@@ -107,7 +107,7 @@ static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb,
 	mdata->entropy = opa_vnic_calc_entropy(skb);
 	mdata->vl = opa_vnic_get_vl(adapter, skb);
 	rc = adapter->rn_ops->ndo_select_queue(netdev, skb,
-					       accel_priv, fallback);
+					       sb_dev, fallback);
 	skb_pull(skb, sizeof(*mdata));
 	return rc;
 }

drivers/net/bonding/bond_main.c

@@ -4094,7 +4094,8 @@ static inline int bond_slave_override(struct bonding *bond,
 
 
 static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     void *accel_priv, select_queue_fallback_t fallback)
+			     struct net_device *sb_dev,
+			     select_queue_fallback_t fallback)
 {
 	/* This helper function exists to help dev_pick_tx get the correct
 	 * destination queue.  Using a helper function skips a call to

drivers/net/ethernet/amazon/ena/ena_netdev.c

@@ -2213,7 +2213,8 @@ static void ena_netpoll(struct net_device *netdev)
 #endif /* CONFIG_NET_POLL_CONTROLLER */
 
 static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    void *accel_priv, select_queue_fallback_t fallback)
+			    struct net_device *sb_dev,
+			    select_queue_fallback_t fallback)
 {
 	u16 qid;
 	/* we suspect that this is good for in--kernel network services that
@@ -2223,7 +2224,7 @@ static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb,
 	if (skb_rx_queue_recorded(skb))
 		qid = skb_get_rx_queue(skb);
 	else
-		qid = fallback(dev, skb);
+		qid = fallback(dev, skb, NULL);
 
 	return qid;
 }

drivers/net/ethernet/broadcom/bcmsysport.c

@@ -2107,7 +2107,7 @@ static const struct ethtool_ops bcm_sysport_ethtool_ops = {
 };
 
 static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
-				    void *accel_priv,
+				    struct net_device *sb_dev,
 				    select_queue_fallback_t fallback)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
@@ -2116,15 +2116,15 @@ static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
 	unsigned int q, port;
 
 	if (!netdev_uses_dsa(dev))
-		return fallback(dev, skb);
+		return fallback(dev, skb, NULL);
 
 	/* DSA tagging layer will have configured the correct queue */
 	q = BRCM_TAG_GET_QUEUE(queue);
 	port = BRCM_TAG_GET_PORT(queue);
 	tx_ring = priv->ring_map[q + port * priv->per_port_num_tx_queues];
 
 	if (unlikely(!tx_ring))
-		return fallback(dev, skb);
+		return fallback(dev, skb, NULL);
 
 	return tx_ring->index;
 }

drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c

@@ -1910,7 +1910,8 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw)
 }
 
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback)
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
@@ -1932,7 +1933,8 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	/* select a non-FCoE queue */
-	return fallback(dev, skb) % (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
+	return fallback(dev, skb, NULL) %
+	       (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
 }
 
 void bnx2x_set_num_queues(struct bnx2x *bp)

drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h

@@ -497,7 +497,8 @@ int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos,
 
 /* select_queue callback */
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback);
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback);
 
 static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
 					struct bnx2x_fastpath *fp,

drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c

@@ -930,7 +930,8 @@ static int setup_sge_queues(struct adapter *adap)
 }
 
 static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     void *accel_priv, select_queue_fallback_t fallback)
+			     struct net_device *sb_dev,
+			     select_queue_fallback_t fallback)
 {
 	int txq;
 
@@ -972,7 +973,7 @@ static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb,
 		return txq;
 	}
 
-	return fallback(dev, skb) % dev->real_num_tx_queues;
+	return fallback(dev, skb, NULL) % dev->real_num_tx_queues;
 }
 
 static int closest_timer(const struct sge *s, int time)

drivers/net/ethernet/hisilicon/hns/hns_enet.c

@@ -2022,7 +2022,8 @@ static void hns_nic_get_stats64(struct net_device *ndev,
 
 static u16
 hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb,
-		     void *accel_priv, select_queue_fallback_t fallback)
+		     struct net_device *sb_dev,
+		     select_queue_fallback_t fallback)
 {
 	struct ethhdr *eth_hdr = (struct ethhdr *)skb->data;
 	struct hns_nic_priv *priv = netdev_priv(ndev);
@@ -2032,7 +2033,7 @@ hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	    is_multicast_ether_addr(eth_hdr->h_dest))
 		return 0;
 	else
-		return fallback(ndev, skb);
+		return fallback(ndev, skb, NULL);
 }
 
 static const struct net_device_ops hns_nic_netdev_ops = {

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -5275,6 +5275,8 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
 			     struct ixgbe_fwd_adapter *accel)
 {
+	u16 rss_i = adapter->ring_feature[RING_F_RSS].indices;
+	int num_tc = netdev_get_num_tc(adapter->netdev);
 	struct net_device *vdev = accel->netdev;
 	int i, baseq, err;
 
@@ -5286,6 +5288,11 @@ static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
 	accel->rx_base_queue = baseq;
 	accel->tx_base_queue = baseq;
 
+	/* record configuration for macvlan interface in vdev */
+	for (i = 0; i < num_tc; i++)
+		netdev_bind_sb_channel_queue(adapter->netdev, vdev,
+					     i, rss_i, baseq + (rss_i * i));
+
 	for (i = 0; i < adapter->num_rx_queues_per_pool; i++)
 		adapter->rx_ring[baseq + i]->netdev = vdev;
 
@@ -5310,6 +5317,10 @@ static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
 
 	netdev_err(vdev, "L2FW offload disabled due to L2 filter error\n");
 
+	/* unbind the queues and drop the subordinate channel config */
+	netdev_unbind_sb_channel(adapter->netdev, vdev);
+	netdev_set_sb_channel(vdev, 0);
+
 	clear_bit(accel->pool, adapter->fwd_bitmask);
 	kfree(accel);
 
@@ -8197,25 +8208,25 @@ static void ixgbe_atr(struct ixgbe_ring *ring,
 					      input, common, ring->queue_index);
 }
 
+#ifdef IXGBE_FCOE
 static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
-			      void *accel_priv, select_queue_fallback_t fallback)
+			      struct net_device *sb_dev,
+			      select_queue_fallback_t fallback)
 {
-	struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
 	struct ixgbe_adapter *adapter;
-	int txq;
-#ifdef IXGBE_FCOE
 	struct ixgbe_ring_feature *f;
-#endif
+	int txq;
 
-	if (fwd_adapter) {
-		adapter = netdev_priv(dev);
-		txq = reciprocal_scale(skb_get_hash(skb),
-				       adapter->num_rx_queues_per_pool);
+	if (sb_dev) {
+		u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
+		struct net_device *vdev = sb_dev;
 
-		return txq + fwd_adapter->tx_base_queue;
-	}
+		txq = vdev->tc_to_txq[tc].offset;
+		txq += reciprocal_scale(skb_get_hash(skb),
+					vdev->tc_to_txq[tc].count);
 
-#ifdef IXGBE_FCOE
+		return txq;
+	}
 
 	/*
 	 * only execute the code below if protocol is FCoE
@@ -8226,11 +8237,11 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 	case htons(ETH_P_FIP):
 		adapter = netdev_priv(dev);
 
-		if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)
+		if (!sb_dev && (adapter->flags & IXGBE_FLAG_FCOE_ENABLED))
 			break;
 		/* fall through */
 	default:
-		return fallback(dev, skb);
+		return fallback(dev, skb, sb_dev);
 	}
 
 	f = &adapter->ring_feature[RING_F_FCOE];
@@ -8242,11 +8253,9 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 		txq -= f->indices;
 
 	return txq + f->offset;
-#else
-	return fallback(dev, skb);
-#endif
 }
 
+#endif
 static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
 			       struct xdp_frame *xdpf)
 {
@@ -8766,6 +8775,11 @@ static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data)
 	/* if we cannot find a free pool then disable the offload */
 	netdev_err(vdev, "L2FW offload disabled due to lack of queue resources\n");
 	macvlan_release_l2fw_offload(vdev);
+
+	/* unbind the queues and drop the subordinate channel config */
+	netdev_unbind_sb_channel(adapter->netdev, vdev);
+	netdev_set_sb_channel(vdev, 0);
+
 	kfree(accel);
 
 	return 0;
@@ -9769,6 +9783,13 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 	if (!macvlan_supports_dest_filter(vdev))
 		return ERR_PTR(-EMEDIUMTYPE);
 
+	/* We need to lock down the macvlan to be a single queue device so that
+	 * we can reuse the tc_to_txq field in the macvlan netdev to represent
+	 * the queue mapping to our netdev.
+	 */
+	if (netif_is_multiqueue(vdev))
+		return ERR_PTR(-ERANGE);
+
 	pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
 	if (pool == adapter->num_rx_pools) {
 		u16 used_pools = adapter->num_vfs + adapter->num_rx_pools;
@@ -9825,6 +9846,7 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 		return ERR_PTR(-ENOMEM);
 
 	set_bit(pool, adapter->fwd_bitmask);
+	netdev_set_sb_channel(vdev, pool);
 	accel->pool = pool;
 	accel->netdev = vdev;
 
@@ -9866,6 +9888,10 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
 		ring->netdev = NULL;
 	}
 
+	/* unbind the queues and drop the subordinate channel config */
+	netdev_unbind_sb_channel(pdev, accel->netdev);
+	netdev_set_sb_channel(accel->netdev, 0);
+
 	clear_bit(accel->pool, adapter->fwd_bitmask);
 	kfree(accel);
 }
@@ -10026,7 +10052,6 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_open		= ixgbe_open,
 	.ndo_stop		= ixgbe_close,
 	.ndo_start_xmit		= ixgbe_xmit_frame,
-	.ndo_select_queue	= ixgbe_select_queue,
 	.ndo_set_rx_mode	= ixgbe_set_rx_mode,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= ixgbe_set_mac,
@@ -10049,6 +10074,7 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_poll_controller	= ixgbe_netpoll,
 #endif
 #ifdef IXGBE_FCOE
+	.ndo_select_queue	= ixgbe_select_queue,
 	.ndo_fcoe_ddp_setup = ixgbe_fcoe_ddp_get,
 	.ndo_fcoe_ddp_target = ixgbe_fcoe_ddp_target,
 	.ndo_fcoe_ddp_done = ixgbe_fcoe_ddp_put,

drivers/net/ethernet/lantiq_etop.c

@@ -563,14 +563,6 @@ ltq_etop_set_multicast_list(struct net_device *dev)
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
-static u16
-ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb,
-		      void *accel_priv, select_queue_fallback_t fallback)
-{
-	/* we are currently only using the first queue */
-	return 0;
-}
-
 static int
 ltq_etop_init(struct net_device *dev)
 {
@@ -641,7 +633,7 @@ static const struct net_device_ops ltq_eth_netdev_ops = {
 	.ndo_set_mac_address = ltq_etop_set_mac_address,
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_set_rx_mode = ltq_etop_set_multicast_list,
-	.ndo_select_queue = ltq_etop_select_queue,
+	.ndo_select_queue = dev_pick_tx_zero,
 	.ndo_init = ltq_etop_init,
 	.ndo_tx_timeout = ltq_etop_tx_timeout,
 };

drivers/net/ethernet/mellanox/mlx4/en_tx.c

@@ -688,15 +688,16 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc,
 }
 
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
-			 void *accel_priv, select_queue_fallback_t fallback)
+			 struct net_device *sb_dev,
+			 select_queue_fallback_t fallback)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	u16 rings_p_up = priv->num_tx_rings_p_up;
 
 	if (netdev_get_num_tc(dev))
-		return fallback(dev, skb);
+		return fallback(dev, skb, NULL);
 
-	return fallback(dev, skb) % rings_p_up;
+	return fallback(dev, skb, NULL) % rings_p_up;
 }
 
 static void mlx4_bf_copy(void __iomem *dst, const void *src,

drivers/net/ethernet/mellanox/mlx4/mlx4_en.h

@@ -699,7 +699,8 @@ void mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
 
 void mlx4_en_tx_irq(struct mlx4_cq *mcq);
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
-			 void *accel_priv, select_queue_fallback_t fallback);
+			 struct net_device *sb_dev,
+			 select_queue_fallback_t fallback);
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 			       struct mlx4_en_rx_alloc *frame,

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

@@ -865,7 +865,8 @@ struct mlx5e_profile {
 void mlx5e_build_ptys2ethtool_map(void);
 
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback);
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback);
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
 netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 			  struct mlx5e_tx_wqe *wqe, u16 pi);

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

@@ -111,10 +111,11 @@ static inline int mlx5e_get_dscp_up(struct mlx5e_priv *priv, struct sk_buff *skb
 #endif
 
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback)
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	int channel_ix = fallback(dev, skb);
+	int channel_ix = fallback(dev, skb, NULL);
 	u16 num_channels;
 	int up = 0;
 

drivers/net/ethernet/renesas/ravb_main.c

@@ -1656,7 +1656,8 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 }
 
 static u16 ravb_select_queue(struct net_device *ndev, struct sk_buff *skb,
-			     void *accel_priv, select_queue_fallback_t fallback)
+			     struct net_device *sb_dev,
+			     select_queue_fallback_t fallback)
 {
 	/* If skb needs TX timestamp, it is handled in network control queue */
 	return (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) ? RAVB_NC :