[NET]: Avoid copying TCP packets unnecessarily

[deliverable/linux.git] / net / core / dev.c

diff --git a/net/core/dev.c b/net/core/dev.c
index 1e169a541ce76b617601a462571af418627ac68a..38b03da5c1ca93d061cfe250195bbfc8898b9da6 100644 (file)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -557,6 +557,7 @@ __setup("netdev=", netdev_boot_setup);
 
 /**
  *     __dev_get_by_name       - find a device by its name
+ *     @net: the applicable net namespace
  *     @name: name to find
  *
  *     Find an interface by name. Must be called under RTNL semaphore
@@ -581,6 +582,7 @@ struct net_device *__dev_get_by_name(struct net *net, const char *name)
 
 /**
  *     dev_get_by_name         - find a device by its name
+ *     @net: the applicable net namespace
  *     @name: name to find
  *
  *     Find an interface by name. This can be called from any
@@ -604,6 +606,7 @@ struct net_device *dev_get_by_name(struct net *net, const char *name)
 
 /**
  *     __dev_get_by_index - find a device by its ifindex
+ *     @net: the applicable net namespace
  *     @ifindex: index of device
  *
  *     Search for an interface by index. Returns %NULL if the device
@@ -629,6 +632,7 @@ struct net_device *__dev_get_by_index(struct net *net, int ifindex)
 
 /**
  *     dev_get_by_index - find a device by its ifindex
+ *     @net: the applicable net namespace
  *     @ifindex: index of device
  *
  *     Search for an interface by index. Returns NULL if the device
@@ -651,6 +655,7 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex)
 
 /**
  *     dev_getbyhwaddr - find a device by its hardware address
+ *     @net: the applicable net namespace
  *     @type: media type of device
  *     @ha: hardware address
  *
@@ -709,6 +714,7 @@ EXPORT_SYMBOL(dev_getfirstbyhwtype);
 
 /**
  *     dev_get_by_flags - find any device with given flags
+ *     @net: the applicable net namespace
  *     @if_flags: IFF_* values
  *     @mask: bitmask of bits in if_flags to check
  *
@@ -948,6 +954,7 @@ void netdev_state_change(struct net_device *dev)
 
 /**
  *     dev_load        - load a network module
+ *     @net: the applicable net namespace
  *     @name: name of interface
  *
  *     If a network interface is not present and the process has suitable
@@ -1185,7 +1192,7 @@ int unregister_netdevice_notifier(struct notifier_block *nb)
 /**
  *     call_netdevice_notifiers - call all network notifier blocks
  *      @val: value passed unmodified to notifier function
- *      @v:   pointer passed unmodified to notifier function
+ *      @dev: net_device pointer passed unmodified to notifier function
  *
  *     Call all network notifier blocks.  Parameters and return value
  *     are as for raw_notifier_call_chain().
@@ -1355,22 +1362,21 @@ int skb_checksum_help(struct sk_buff *skb)
                goto out_set_summed;
        }
 
-       if (skb_cloned(skb)) {
+       offset = skb->csum_start - skb_headroom(skb);
+       BUG_ON(offset >= skb_headlen(skb));
+       csum = skb_checksum(skb, offset, skb->len - offset, 0);
+
+       offset += skb->csum_offset;
+       BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb));
+
+       if (skb_cloned(skb) &&
+           !skb_clone_writable(skb, offset + sizeof(__sum16))) {
                ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
                if (ret)
                        goto out;
        }
 
-       offset = skb->csum_start - skb_headroom(skb);
-       BUG_ON(offset > (int)skb->len);
-       csum = skb_checksum(skb, offset, skb->len-offset, 0);
-
-       offset = skb_headlen(skb) - offset;
-       BUG_ON(offset <= 0);
-       BUG_ON(skb->csum_offset + 2 > offset);
-
-       *(__sum16 *)(skb->head + skb->csum_start + skb->csum_offset) =
-               csum_fold(csum);
+       *(__sum16 *)(skb->data + offset) = csum_fold(csum);
 out_set_summed:
        skb->ip_summed = CHECKSUM_NONE;
 out:
@@ -1942,27 +1948,51 @@ static int ing_filter(struct sk_buff *skb)
        struct Qdisc *q;
        struct net_device *dev = skb->dev;
        int result = TC_ACT_OK;
+       u32 ttl = G_TC_RTTL(skb->tc_verd);
 
-       if (dev->qdisc_ingress) {
-               __u32 ttl = (__u32) G_TC_RTTL(skb->tc_verd);
-               if (MAX_RED_LOOP < ttl++) {
-                       printk(KERN_WARNING "Redir loop detected Dropping packet (%d->%d)\n",
-                               skb->iif, skb->dev->ifindex);
-                       return TC_ACT_SHOT;
-               }
+       if (MAX_RED_LOOP < ttl++) {
+               printk(KERN_WARNING
+                      "Redir loop detected Dropping packet (%d->%d)\n",
+                      skb->iif, dev->ifindex);
+               return TC_ACT_SHOT;
+       }
+
+       skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl);
+       skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
 
-               skb->tc_verd = SET_TC_RTTL(skb->tc_verd,ttl);
+       spin_lock(&dev->ingress_lock);
+       if ((q = dev->qdisc_ingress) != NULL)
+               result = q->enqueue(skb, q);
+       spin_unlock(&dev->ingress_lock);
 
-               skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_INGRESS);
+       return result;
+}
+
+static inline struct sk_buff *handle_ing(struct sk_buff *skb,
+                                        struct packet_type **pt_prev,
+                                        int *ret, struct net_device *orig_dev)
+{
+       if (!skb->dev->qdisc_ingress)
+               goto out;
 
-               spin_lock(&dev->ingress_lock);
-               if ((q = dev->qdisc_ingress) != NULL)
-                       result = q->enqueue(skb, q);
-               spin_unlock(&dev->ingress_lock);
+       if (*pt_prev) {
+               *ret = deliver_skb(skb, *pt_prev, orig_dev);
+               *pt_prev = NULL;
+       } else {
+               /* Huh? Why does turning on AF_PACKET affect this? */
+               skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
+       }
 
+       switch (ing_filter(skb)) {
+       case TC_ACT_SHOT:
+       case TC_ACT_STOLEN:
+               kfree_skb(skb);
+               return NULL;
        }
 
-       return result;
+out:
+       skb->tc_verd = 0;
+       return skb;
 }
 #endif
 
@@ -2014,21 +2044,9 @@ int netif_receive_skb(struct sk_buff *skb)
        }
 
 #ifdef CONFIG_NET_CLS_ACT
-       if (pt_prev) {
-               ret = deliver_skb(skb, pt_prev, orig_dev);
-               pt_prev = NULL; /* noone else should process this after*/
-       } else {
-               skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
-       }
-
-       ret = ing_filter(skb);
-
-       if (ret == TC_ACT_SHOT || (ret == TC_ACT_STOLEN)) {
-               kfree_skb(skb);
+       skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
+       if (!skb)
                goto out;
-       }
-
-       skb->tc_verd = 0;
 ncls:
 #endif
 
@@ -2097,7 +2115,7 @@ static int process_backlog(struct napi_struct *napi, int quota)
 
 /**
  * __napi_schedule - schedule for receive
- * @napi: entry to schedule
+ * @n: entry to schedule
  *
  * The entry's receive function will be scheduled to run
  */
@@ -3259,6 +3277,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 
 /**
  *     dev_ioctl       -       network device ioctl
+ *     @net: the applicable net namespace
  *     @cmd: command to issue
  *     @arg: pointer to a struct ifreq in user space
  *
@@ -3436,6 +3455,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 
 /**
  *     dev_new_index   -       allocate an ifindex
+ *     @net: the applicable net namespace
  *
  *     Returns a suitable unique value for a new device interface
  *     number.  The caller must hold the rtnl semaphore or the