Currently, the tx queue were selected implicitly in ndo_dfwd_start_xmit(). The
will cause several issues:
- NETIF_F_LLTX was forced for macvlan device in this case which lead extra lock
contention.
- 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 select queue method just for l2 forwarding
offload (ndo_dfwd_select_queue), and introducing dfwd_direct_xmit() to do the
queue selecting and transmitting for l2 forwarding.
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().
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@xxxxxxxxx>
Cc: Neil Horman <nhorman@xxxxxxxxxxxxx>
Cc: e1000-devel@xxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Jason Wang <jasowang@xxxxxxxxxx>
---
index 4fc1722..bc2b03f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2538,6 +2538,32 @@ static inline int skb_needs_linearize(struct sk_buff *skb,
!(features & NETIF_F_SG)));
}
+int dfwd_direct_xmit(struct sk_buff *skb, struct net_device *dev,
+ void *accel_priv)
+{
+ struct netdev_queue *txq;
+ int ret = NETDEV_TX_BUSY;
+ int index;
+
+ BUG_ON(!dev->netdev_ops->ndo_dfwd_select_queue);
+ index = dev->netdev_ops->ndo_dfwd_select_queue(dev, skb,
+ accel_priv);
+
+ local_bh_disable();
+
+ skb_set_queue_mapping(skb, index);
+ txq = netdev_get_tx_queue(dev, index);
+
+ HARD_TX_LOCK(dev, txq, smp_processor_id());
+ if (!netif_xmit_frozen_or_stopped(txq))
+ ret = dev_hard_start_xmit(skb, dev, txq, accel_priv);
+ HARD_TX_UNLOCK(dev, txq);
+
+ local_bh_enable();
+ return ret;
+}
+EXPORT_SYMBOL_GPL(dfwd_direct_xmit);
+
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, void *accel_priv)
{
@@ -2611,7 +2637,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
rc = ops->ndo_start_xmit(skb, dev);
trace_net_dev_xmit(skb, rc, dev, skb_len);
- if (rc == NETDEV_TX_OK && txq)
+ if (rc == NETDEV_TX_OK)
txq_trans_update(txq);
return rc;
}