net: allow to propagate errors through ->ndo_hard_start_xmit()

Currently the ->ndo_hard_start_xmit() callbacks are only permitted to return
one of the NETDEV_TX codes. This prevents any kind of error propagation for
virtual devices, like queue congestion of the underlying device in case of
layered devices, or unreachability in case of tunnels.

This patches changes the NET_XMIT codes to avoid clashes with the NETDEV_TX
codes and changes the two callers of dev_hard_start_xmit() to expect either
errno codes, NET_XMIT codes or NETDEV_TX codes as return value.

In case of qdisc_restart(), all non NETDEV_TX codes are mapped to NETDEV_TX_OK
since no error propagation is possible when using qdiscs. In case of
dev_queue_xmit(), the error is propagated upwards.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 34 insertions, 7 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index ad8e320ceba7..548340b57296 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1757,7 +1757,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
                         struct netdev_queue *txq)
 {
         const struct net_device_ops *ops = dev->netdev_ops;
-        int rc;
+        int rc = NETDEV_TX_OK;
 
         if (likely(!skb->next)) {
                 if (!list_empty(&ptype_all))
@@ -1805,6 +1805,8 @@ gso:
                 nskb->next = NULL;
                 rc = ops->ndo_start_xmit(nskb, dev);
                 if (unlikely(rc != NETDEV_TX_OK)) {
+                        if (rc & ~NETDEV_TX_MASK)
+                                goto out_kfree_gso_skb;
                         nskb->next = skb->next;
                         skb->next = nskb;
                         return rc;
@@ -1814,11 +1816,12 @@ gso:
                         return NETDEV_TX_BUSY;
         } while (skb->next);
 
-        skb->destructor = DEV_GSO_CB(skb)->destructor;
-
+out_kfree_gso_skb:
+        if (likely(skb->next == NULL))
+                skb->destructor = DEV_GSO_CB(skb)->destructor;
 out_kfree_skb:
         kfree_skb(skb);
-        return NETDEV_TX_OK;
+        return rc;
 }
 
 static u32 skb_tx_hashrnd;
@@ -1906,6 +1909,23 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
         return rc;
 }
 
+static inline bool dev_xmit_complete(int rc)
+{
+        /* successful transmission */
+        if (rc == NETDEV_TX_OK)
+                return true;
+
+        /* error while transmitting, driver consumed skb */
+        if (rc < 0)
+                return true;
+
+        /* error while queueing to a different device, driver consumed skb */
+        if (rc & NET_XMIT_MASK)
+                return true;
+
+        return false;
+}
+
 /**
  *      dev_queue_xmit - transmit a buffer
  *      @skb: buffer to transmit
@@ -2003,8 +2023,8 @@ gso:
                         HARD_TX_LOCK(dev, txq, cpu);
 
                         if (!netif_tx_queue_stopped(txq)) {
-                                rc = NET_XMIT_SUCCESS;
-                                if (!dev_hard_start_xmit(skb, dev, txq)) {
+                                rc = dev_hard_start_xmit(skb, dev, txq);
+                                if (dev_xmit_complete(rc)) {
                                         HARD_TX_UNLOCK(dev, txq);
                                         goto out;
                                 }
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 4ae6aa562f2b..b13821ad2fb6 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -120,8 +120,15 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 
         HARD_TX_LOCK(dev, txq, smp_processor_id());
         if (!netif_tx_queue_stopped(txq) &&
-            !netif_tx_queue_frozen(txq))
+            !netif_tx_queue_frozen(txq)) {
                 ret = dev_hard_start_xmit(skb, dev, txq);
+
+                /* an error implies that the skb was consumed */
+                if (ret < 0)
+                        ret = NETDEV_TX_OK;
+                /* all NET_XMIT codes map to NETDEV_TX_OK */
+                ret &= ~NET_XMIT_MASK;
+        }
         HARD_TX_UNLOCK(dev, txq);
 
         spin_lock(root_lock);