net: core: explicitly select a txq before doing l2 forwarding

Currently, the tx queue were selected implicitly in ndo_dfwd_start_xmit(). The
will cause several issues:

- NETIF_F_LLTX were removed for macvlan, so txq lock were done for macvlan
  instead of lower device which misses the necessary txq synchronization for
  lower device such as txq stopping or frozen required by dev watchdog or
  control path.
- dev_hard_start_xmit() was called with NULL txq which bypasses the net device
  watchdog.
- dev_hard_start_xmit() does not check txq everywhere which will lead a crash
  when tso is disabled for lower device.

Fix this by explicitly introducing a new param for .ndo_select_queue() for just
selecting queues in the case of l2 forwarding offload. netdev_pick_tx() was also
extended to accept this parameter and dev_queue_xmit_accel() was used to do l2
forwarding transmission.

With this fixes, NETIF_F_LLTX could be preserved for macvlan and there's no need
to check txq against NULL in dev_hard_start_xmit(). Also there's no need to keep
a dedicated ndo_dfwd_start_xmit() and we can just reuse the code of
dev_queue_xmit() to do the transmission.

In the future, it was also required for macvtap l2 forwarding support since it
provides a necessary synchronization method.

Cc: John Fastabend <john.r.fastabend@intel.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: e1000-devel@lists.sourceforge.net
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

15 files changed, 42 insertions, 39 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 398e299ee1bd..4b8c58b0ec24 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3732,7 +3732,8 @@ static inline int bond_slave_override(struct bonding *bond,
 }
 
 
-static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
+                             void *accel_priv)
 {
         /*
          * This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 550412088dd0..bf811565ee24 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1833,7 +1833,8 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw)
                 bnx2x_napi_disable_cnic(bp);
 }
 
-u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb)
+u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
+                       void *accel_priv)
 {
         struct bnx2x *bp = netdev_priv(dev);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index da8fcaa74495..41f3ca5ad972 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -524,7 +524,8 @@ int bnx2x_set_vf_mac(struct net_device *dev, int queue, u8 *mac);
 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);
+u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
+                       void *accel_priv);
 
 static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
                                         struct bnx2x_fastpath *fp,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index cc06854296a3..5bcc870f8367 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6827,12 +6827,20 @@ static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size)
         return __ixgbe_maybe_stop_tx(tx_ring, size);
 }
 
-#ifdef IXGBE_FCOE
-static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
+                              void *accel_priv)
 {
+        struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
+#ifdef IXGBE_FCOE
         struct ixgbe_adapter *adapter;
         struct ixgbe_ring_feature *f;
         int txq;
+#endif
+
+        if (fwd_adapter)
+                return skb->queue_mapping + fwd_adapter->tx_base_queue;
+
+#ifdef IXGBE_FCOE
 
         /*
          * only execute the code below if protocol is FCoE
@@ -6858,9 +6866,11 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
                 txq -= f->indices;
 
         return txq + f->offset;
+#else
+        return __netdev_pick_tx(dev, skb);
+#endif
 }
 
-#endif
 netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
                           struct ixgbe_adapter *adapter,
                           struct ixgbe_ring *tx_ring)
@@ -7629,27 +7639,11 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
         kfree(fwd_adapter);
 }
 
-static netdev_tx_t ixgbe_fwd_xmit(struct sk_buff *skb,
-                                  struct net_device *dev,
-                                  void *priv)
-{
-        struct ixgbe_fwd_adapter *fwd_adapter = priv;
-        unsigned int queue;
-        struct ixgbe_ring *tx_ring;
-
-        queue = skb->queue_mapping + fwd_adapter->tx_base_queue;
-        tx_ring = fwd_adapter->real_adapter->tx_ring[queue];
-
-        return __ixgbe_xmit_frame(skb, dev, tx_ring);
-}
-
 static const struct net_device_ops ixgbe_netdev_ops = {
         .ndo_open               = ixgbe_open,
         .ndo_stop               = ixgbe_close,
         .ndo_start_xmit         = ixgbe_xmit_frame,
-#ifdef IXGBE_FCOE
         .ndo_select_queue       = ixgbe_select_queue,
-#endif
         .ndo_set_rx_mode        = ixgbe_set_rx_mode,
         .ndo_validate_addr      = eth_validate_addr,
         .ndo_set_mac_address    = ixgbe_set_mac,
@@ -7689,7 +7683,6 @@ static const struct net_device_ops ixgbe_netdev_ops = {
         .ndo_bridge_getlink     = ixgbe_ndo_bridge_getlink,
         .ndo_dfwd_add_station   = ixgbe_fwd_add,
         .ndo_dfwd_del_station   = ixgbe_fwd_del,
-        .ndo_dfwd_start_xmit    = ixgbe_fwd_xmit,
 };
 
 /**
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 6a6c1f76d8e0..ec94a20d7099 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -619,7 +619,8 @@ ltq_etop_set_multicast_list(struct net_device *dev)
 }
 
 static u16
-ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb)
+ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb,
+                      void *accel_priv)
 {
         /* we are currently only using the first queue */
         return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index f54ebd5a1702..a7fcd593b2db 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -592,7 +592,8 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, struct sk_buff *sk
         }
 }
 
-u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb)
+u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
+                         void *accel_priv)
 {
         struct mlx4_en_priv *priv = netdev_priv(dev);
         u16 rings_p_up = priv->num_tx_rings_p_up;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index f3758de59c05..d5758adceaa2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -714,7 +714,8 @@ int mlx4_en_set_cq_moder(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
 int 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);
+u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
+                         void *accel_priv);
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 628b736e5ae7..0e9fb3301b11 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -2080,7 +2080,8 @@ static int tile_net_tx(struct sk_buff *skb, struct net_device *dev)
 }
 
 /* Return subqueue id on this core (one per core). */
-static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb,
+                                 void *accel_priv)
 {
         return smp_processor_id();
 }
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 5360f73c9817..bc8faaec33f5 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -299,7 +299,7 @@ netdev_tx_t macvlan_start_xmit(struct sk_buff *skb,
 
         if (vlan->fwd_priv) {
                 skb->dev = vlan->lowerdev;
-                ret = dev_hard_start_xmit(skb, skb->dev, NULL, vlan->fwd_priv);
+                ret = dev_queue_xmit_accel(skb, vlan->fwd_priv);
         } else {
                 ret = macvlan_queue_xmit(skb, dev);
         }
@@ -365,10 +365,8 @@ static int macvlan_open(struct net_device *dev)
                  */
                 if (IS_ERR_OR_NULL(vlan->fwd_priv)) {
                         vlan->fwd_priv = NULL;
-                } else {
-                        dev->features &= ~NETIF_F_LLTX;
+                } else
                         return 0;
-                }
         }
 
         err = -EBUSY;
@@ -702,8 +700,7 @@ static netdev_features_t macvlan_fix_features(struct net_device *dev,
         features = netdev_increment_features(vlan->lowerdev->features,
                                              features,
                                              mask);
-        if (!vlan->fwd_priv)
-                features |= NETIF_F_LLTX;
+        features |= NETIF_F_LLTX;
 
         return features;
 }
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 736050d6b451..b75ae5bde673 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1647,7 +1647,8 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev)
         return NETDEV_TX_OK;
 }
 
-static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb,
+                             void *accel_priv)
 {
         /*
          * This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 7c8343a4f918..ecec8029c5e8 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -348,7 +348,8 @@ unlock:
  * different rxq no. here. If we could not get rxhash, then we would
  * hope the rxq no. may help here.
  */
-static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
+                            void *accel_priv)
 {
         struct tun_struct *tun = netdev_priv(dev);
         struct tun_flow_entry *e;
diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c
index 78e8a6666cc6..8bb8988c435c 100644
--- a/drivers/net/wireless/mwifiex/main.c
+++ b/drivers/net/wireless/mwifiex/main.c
@@ -746,7 +746,8 @@ static struct net_device_stats *mwifiex_get_stats(struct net_device *dev)
 }
 
 static u16
-mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb)
+mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb,
+                                void *accel_priv)
 {
         skb->priority = cfg80211_classify8021d(skb);
         return mwifiex_1d_to_wmm_queue[skb->priority];
diff --git a/drivers/staging/bcm/Bcmnet.c b/drivers/staging/bcm/Bcmnet.c
index 53fee2f9a498..8dfdd2732bdc 100644
--- a/drivers/staging/bcm/Bcmnet.c
+++ b/drivers/staging/bcm/Bcmnet.c
@@ -39,7 +39,8 @@ static INT bcm_close(struct net_device *dev)
         return 0;
 }
 
-static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb,
+                            void *accel_priv)
 {
         return ClassifyPacket(netdev_priv(dev), skb);
 }
diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c
index 235d2b1ec593..eedffed17e39 100644
--- a/drivers/staging/netlogic/xlr_net.c
+++ b/drivers/staging/netlogic/xlr_net.c
@@ -306,7 +306,8 @@ static netdev_tx_t xlr_net_start_xmit(struct sk_buff *skb,
         return NETDEV_TX_OK;
 }
 
-static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb)
+static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb,
+                                void *accel_priv)
 {
         return (u16)smp_processor_id();
 }
diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
index 17659bb04bef..dd69e344e409 100644
--- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
@@ -652,7 +652,8 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb)
         return dscp >> 5;
 }
 
-static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
+                            void *accel_priv)
 {
         struct adapter  *padapter = rtw_netdev_priv(dev);
         struct mlme_priv *pmlmepriv = &padapter->mlmepriv;