5 files changed, 164 insertions, 150 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 1e169a541ce..38b03da5c1c 100644
--- 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
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index c52df858d0b..cd3af59b38a 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -481,6 +481,8 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, const void *pkey,
 	if (!creat)
 		goto out;
 
+	ASSERT_RTNL();
+
 	n = kmalloc(sizeof(*n) + key_len, GFP_KERNEL);
 	if (!n)
 		goto out;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 909a03d6c0e..6628e457ddc 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -396,28 +396,22 @@ static struct attribute_group wireless_group = {
 #endif /* CONFIG_SYSFS */
 
 #ifdef CONFIG_HOTPLUG
-static int netdev_uevent(struct device *d, char **envp,
-			 int num_envp, char *buf, int size)
+static int netdev_uevent(struct device *d, struct kobj_uevent_env *env)
 {
 	struct net_device *dev = to_net_dev(d);
-	int retval, len = 0, i = 0;
+	int retval;
 
 	/* pass interface to uevent. */
-	retval = add_uevent_var(envp, num_envp, &i,
-				buf, size, &len,
-				"INTERFACE=%s", dev->name);
+	retval = add_uevent_var(env, "INTERFACE=%s", dev->name);
 	if (retval)
 		goto exit;
 
 	/* pass ifindex to uevent.
 	 * ifindex is useful as it won't change (interface name may change)
 	 * and is what RtNetlink uses natively. */
-	retval = add_uevent_var(envp, num_envp, &i,
-				buf, size, &len,
-				"IFINDEX=%d", dev->ifindex);
+	retval = add_uevent_var(env, "IFINDEX=%d", dev->ifindex);
 
 exit:
-	envp[i] = NULL;
 	return retval;
 }
 #endif
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 944189d9632..70d9b5da96a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -362,6 +362,97 @@ void kfree_skb(struct sk_buff *skb)
 	__kfree_skb(skb);
 }
 
+static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
+{
+	new->tstamp		= old->tstamp;
+	new->dev		= old->dev;
+	new->transport_header	= old->transport_header;
+	new->network_header	= old->network_header;
+	new->mac_header		= old->mac_header;
+	new->dst		= dst_clone(old->dst);
+#ifdef CONFIG_INET
+	new->sp			= secpath_get(old->sp);
+#endif
+	memcpy(new->cb, old->cb, sizeof(old->cb));
+	new->csum_start		= old->csum_start;
+	new->csum_offset	= old->csum_offset;
+	new->local_df		= old->local_df;
+	new->pkt_type		= old->pkt_type;
+	new->ip_summed		= old->ip_summed;
+	skb_copy_queue_mapping(new, old);
+	new->priority		= old->priority;
+#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
+	new->ipvs_property	= old->ipvs_property;
+#endif
+	new->protocol		= old->protocol;
+	new->mark		= old->mark;
+	__nf_copy(new, old);
+#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
+    defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
+	new->nf_trace		= old->nf_trace;
+#endif
+#ifdef CONFIG_NET_SCHED
+	new->tc_index		= old->tc_index;
+#ifdef CONFIG_NET_CLS_ACT
+	new->tc_verd		= old->tc_verd;
+#endif
+#endif
+	skb_copy_secmark(new, old);
+}
+
+static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
+{
+#define C(x) n->x = skb->x
+
+	n->next = n->prev = NULL;
+	n->sk = NULL;
+	__copy_skb_header(n, skb);
+
+	C(len);
+	C(data_len);
+	C(mac_len);
+	n->cloned = 1;
+	n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len;
+	n->nohdr = 0;
+	n->destructor = NULL;
+#ifdef CONFIG_NET_CLS_ACT
+	/* FIXME What is this and why don't we do it in copy_skb_header? */
+	n->tc_verd = SET_TC_VERD(n->tc_verd,0);
+	n->tc_verd = CLR_TC_OK2MUNGE(n->tc_verd);
+	n->tc_verd = CLR_TC_MUNGED(n->tc_verd);
+	C(iif);
+#endif
+	C(truesize);
+	atomic_set(&n->users, 1);
+	C(head);
+	C(data);
+	C(tail);
+	C(end);
+
+	atomic_inc(&(skb_shinfo(skb)->dataref));
+	skb->cloned = 1;
+
+	return n;
+#undef C
+}
+
+/**
+ *	skb_morph	-	morph one skb into another
+ *	@dst: the skb to receive the contents
+ *	@src: the skb to supply the contents
+ *
+ *	This is identical to skb_clone except that the target skb is
+ *	supplied by the user.
+ *
+ *	The target skb is returned upon exit.
+ */
+struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src)
+{
+	skb_release_data(dst);
+	return __skb_clone(dst, src);
+}
+EXPORT_SYMBOL_GPL(skb_morph);
+
 /**
  *	skb_clone	-	duplicate an sk_buff
  *	@skb: buffer to clone
@@ -393,66 +484,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 		n->fclone = SKB_FCLONE_UNAVAILABLE;
 	}
 
-#define C(x) n->x = skb->x
-
-	n->next = n->prev = NULL;
-	n->sk = NULL;
-	C(tstamp);
-	C(dev);
-	C(transport_header);
-	C(network_header);
-	C(mac_header);
-	C(dst);
-	dst_clone(skb->dst);
-	C(sp);
-#ifdef CONFIG_INET
-	secpath_get(skb->sp);
-#endif
-	memcpy(n->cb, skb->cb, sizeof(skb->cb));
-	C(len);
-	C(data_len);
-	C(mac_len);
-	C(csum);
-	C(local_df);
-	n->cloned = 1;
-	n->hdr_len = skb->nohdr ? skb_headroom(skb) : skb->hdr_len;
-	n->nohdr = 0;
-	C(pkt_type);
-	C(ip_summed);
-	skb_copy_queue_mapping(n, skb);
-	C(priority);
-#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
-	C(ipvs_property);
-#endif
-	C(protocol);
-	n->destructor = NULL;
-	C(mark);
-	__nf_copy(n, skb);
-#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
-    defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
-	C(nf_trace);
-#endif
-#ifdef CONFIG_NET_SCHED
-	C(tc_index);
-#ifdef CONFIG_NET_CLS_ACT
-	n->tc_verd = SET_TC_VERD(skb->tc_verd,0);
-	n->tc_verd = CLR_TC_OK2MUNGE(n->tc_verd);
-	n->tc_verd = CLR_TC_MUNGED(n->tc_verd);
-	C(iif);
-#endif
-#endif
-	skb_copy_secmark(n, skb);
-	C(truesize);
-	atomic_set(&n->users, 1);
-	C(head);
-	C(data);
-	C(tail);
-	C(end);
-
-	atomic_inc(&(skb_shinfo(skb)->dataref));
-	skb->cloned = 1;
-
-	return n;
+	return __skb_clone(n, skb);
 }
 
 static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
@@ -463,50 +495,15 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	 */
 	unsigned long offset = new->data - old->data;
 #endif
-	new->sk		= NULL;
-	new->dev	= old->dev;
-	skb_copy_queue_mapping(new, old);
-	new->priority	= old->priority;
-	new->protocol	= old->protocol;
-	new->dst	= dst_clone(old->dst);
-#ifdef CONFIG_INET
-	new->sp		= secpath_get(old->sp);
-#endif
-	new->csum_start = old->csum_start;
-	new->csum_offset = old->csum_offset;
-	new->ip_summed = old->ip_summed;
-	new->transport_header = old->transport_header;
-	new->network_header   = old->network_header;
-	new->mac_header	      = old->mac_header;
+
+	__copy_skb_header(new, old);
+
 #ifndef NET_SKBUFF_DATA_USES_OFFSET
 	/* {transport,network,mac}_header are relative to skb->head */
 	new->transport_header += offset;
 	new->network_header   += offset;
 	new->mac_header	      += offset;
 #endif
-	memcpy(new->cb, old->cb, sizeof(old->cb));
-	new->local_df	= old->local_df;
-	new->fclone	= SKB_FCLONE_UNAVAILABLE;
-	new->pkt_type	= old->pkt_type;
-	new->tstamp	= old->tstamp;
-	new->destructor = NULL;
-	new->mark	= old->mark;
-	__nf_copy(new, old);
-#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
-    defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
-	new->nf_trace	= old->nf_trace;
-#endif
-#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
-	new->ipvs_property = old->ipvs_property;
-#endif
-#ifdef CONFIG_NET_SCHED
-#ifdef CONFIG_NET_CLS_ACT
-	new->tc_verd = old->tc_verd;
-#endif
-	new->tc_index	= old->tc_index;
-#endif
-	skb_copy_secmark(new, old);
-	atomic_set(&new->users, 1);
 	skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size;
 	skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs;
 	skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type;
@@ -685,7 +682,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 	skb->transport_header += off;
 	skb->network_header   += off;
 	skb->mac_header	      += off;
-	skb->csum_start       += off;
+	skb->csum_start       += nhead;
 	skb->cloned   = 0;
 	skb->hdr_len  = 0;
 	skb->nohdr    = 0;
diff --git a/net/core/sock.c b/net/core/sock.c
index 4ed9b507c1e..d45ecdccc6a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -869,6 +869,7 @@ static inline void sock_lock_init(struct sock *sk)
 
 /**
  *	sk_alloc - All socket objects are allocated here
+ *	@net: the applicable net namespace
  *	@family: protocol family
  *	@priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
  *	@prot: struct proto associated with this new sock instance