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>
diff --git a/net/core/dev.c b/net/core/dev.c
index 4fc1722..0ce469e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2539,7 +2539,7 @@
}
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
- struct netdev_queue *txq, void *accel_priv)
+ struct netdev_queue *txq)
{
const struct net_device_ops *ops = dev->netdev_ops;
int rc = NETDEV_TX_OK;
@@ -2605,13 +2605,10 @@
dev_queue_xmit_nit(skb, dev);
skb_len = skb->len;
- if (accel_priv)
- rc = ops->ndo_dfwd_start_xmit(skb, dev, accel_priv);
- else
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;
}
@@ -2627,10 +2624,7 @@
dev_queue_xmit_nit(nskb, dev);
skb_len = nskb->len;
- if (accel_priv)
- rc = ops->ndo_dfwd_start_xmit(nskb, dev, accel_priv);
- else
- rc = ops->ndo_start_xmit(nskb, dev);
+ rc = ops->ndo_start_xmit(nskb, dev);
trace_net_dev_xmit(nskb, rc, dev, skb_len);
if (unlikely(rc != NETDEV_TX_OK)) {
if (rc & ~NETDEV_TX_MASK)
@@ -2811,7 +2805,7 @@
* the BH enable code must have IRQs enabled so that it will not deadlock.
* --BLG
*/
-int dev_queue_xmit(struct sk_buff *skb)
+int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
{
struct net_device *dev = skb->dev;
struct netdev_queue *txq;
@@ -2827,7 +2821,7 @@
skb_update_prio(skb);
- txq = netdev_pick_tx(dev, skb);
+ txq = netdev_pick_tx(dev, skb, accel_priv);
q = rcu_dereference_bh(txq->qdisc);
#ifdef CONFIG_NET_CLS_ACT
@@ -2863,7 +2857,7 @@
if (!netif_xmit_stopped(txq)) {
__this_cpu_inc(xmit_recursion);
- rc = dev_hard_start_xmit(skb, dev, txq, NULL);
+ rc = dev_hard_start_xmit(skb, dev, txq);
__this_cpu_dec(xmit_recursion);
if (dev_xmit_complete(rc)) {
HARD_TX_UNLOCK(dev, txq);
@@ -2892,8 +2886,19 @@
rcu_read_unlock_bh();
return rc;
}
+
+int dev_queue_xmit(struct sk_buff *skb)
+{
+ return __dev_queue_xmit(skb, NULL);
+}
EXPORT_SYMBOL(dev_queue_xmit);
+int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
+{
+ return __dev_queue_xmit(skb, accel_priv);
+}
+EXPORT_SYMBOL(dev_queue_xmit_accel);
+
/*=======================================================================
Receiver routines