Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6:
  [NET]: Require CAP_NET_ADMIN to create tuntap devices.
  [NET]: fix net-core kernel-doc
  [TCP]: Move inclusion of <linux/dmaengine.h> to correct place in <linux/tcp.h>
  [IPSEC]: Handle GSO packets
  [NET]: Added GSO toggle
  [NET]: Add software TSOv4
  [NET]: Add generic segmentation offload
  [NET]: Merge TSO/UFO fields in sk_buff
  [NET]: Prevent transmission after dev_deactivate
  [IPV6] ADDRCONF: Fix default source address selection without CONFIG_IPV6_PRIVACY
  [IPV6]: Fix source address selection.
  [NET]: Avoid allocating skb in skb_pad

3 files changed, 317 insertions, 27 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 195a5e96b2d..ea2469398bd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -116,6 +116,7 @@
 #include <asm/current.h>
 #include <linux/audit.h>
 #include <linux/dmaengine.h>
+#include <linux/err.h>
 
 /*
  *	The list of packet types we will receive (as opposed to discard)
@@ -1048,7 +1049,7 @@ static inline void net_timestamp(struct sk_buff *skb)
  *	taps currently in use.
  */
 
-void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
+static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct packet_type *ptype;
 
@@ -1186,6 +1187,40 @@ out:
 	return ret;
 }
 
+/**
+ *	skb_gso_segment - Perform segmentation on skb.
+ *	@skb: buffer to segment
+ *	@sg: whether scatter-gather is supported on the target.
+ *
+ *	This function segments the given skb and returns a list of segments.
+ */
+struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg)
+{
+	struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
+	struct packet_type *ptype;
+	int type = skb->protocol;
+
+	BUG_ON(skb_shinfo(skb)->frag_list);
+	BUG_ON(skb->ip_summed != CHECKSUM_HW);
+
+	skb->mac.raw = skb->data;
+	skb->mac_len = skb->nh.raw - skb->data;
+	__skb_pull(skb, skb->mac_len);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & 15], list) {
+		if (ptype->type == type && !ptype->dev && ptype->gso_segment) {
+			segs = ptype->gso_segment(skb, sg);
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return segs;
+}
+
+EXPORT_SYMBOL(skb_gso_segment);
+
 /* Take action when hardware reception checksum errors are detected. */
 #ifdef CONFIG_BUG
 void netdev_rx_csum_fault(struct net_device *dev)
@@ -1222,6 +1257,86 @@ static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
 #define illegal_highdma(dev, skb)	(0)
 #endif
 
+struct dev_gso_cb {
+	void (*destructor)(struct sk_buff *skb);
+};
+
+#define DEV_GSO_CB(skb) ((struct dev_gso_cb *)(skb)->cb)
+
+static void dev_gso_skb_destructor(struct sk_buff *skb)
+{
+	struct dev_gso_cb *cb;
+
+	do {
+		struct sk_buff *nskb = skb->next;
+
+		skb->next = nskb->next;
+		nskb->next = NULL;
+		kfree_skb(nskb);
+	} while (skb->next);
+
+	cb = DEV_GSO_CB(skb);
+	if (cb->destructor)
+		cb->destructor(skb);
+}
+
+/**
+ *	dev_gso_segment - Perform emulated hardware segmentation on skb.
+ *	@skb: buffer to segment
+ *
+ *	This function segments the given skb and stores the list of segments
+ *	in skb->next.
+ */
+static int dev_gso_segment(struct sk_buff *skb)
+{
+	struct net_device *dev = skb->dev;
+	struct sk_buff *segs;
+
+	segs = skb_gso_segment(skb, dev->features & NETIF_F_SG &&
+				    !illegal_highdma(dev, skb));
+	if (unlikely(IS_ERR(segs)))
+		return PTR_ERR(segs);
+
+	skb->next = segs;
+	DEV_GSO_CB(skb)->destructor = skb->destructor;
+	skb->destructor = dev_gso_skb_destructor;
+
+	return 0;
+}
+
+int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	if (likely(!skb->next)) {
+		if (netdev_nit)
+			dev_queue_xmit_nit(skb, dev);
+
+		if (!netif_needs_gso(dev, skb))
+			return dev->hard_start_xmit(skb, dev);
+
+		if (unlikely(dev_gso_segment(skb)))
+			goto out_kfree_skb;
+	}
+
+	do {
+		struct sk_buff *nskb = skb->next;
+		int rc;
+
+		skb->next = nskb->next;
+		nskb->next = NULL;
+		rc = dev->hard_start_xmit(nskb, dev);
+		if (unlikely(rc)) {
+			skb->next = nskb;
+			return rc;
+		}
+	} while (skb->next);
+	
+	skb->destructor = DEV_GSO_CB(skb)->destructor;
+
+out_kfree_skb:
+	kfree_skb(skb);
+	return 0;
+}
+
 #define HARD_TX_LOCK(dev, cpu) {			\
 	if ((dev->features & NETIF_F_LLTX) == 0) {	\
 		netif_tx_lock(dev);			\
@@ -1266,6 +1381,10 @@ int dev_queue_xmit(struct sk_buff *skb)
 	struct Qdisc *q;
 	int rc = -ENOMEM;
 
+	/* GSO will handle the following emulations directly. */
+	if (netif_needs_gso(dev, skb))
+		goto gso;
+
 	if (skb_shinfo(skb)->frag_list &&
 	    !(dev->features & NETIF_F_FRAGLIST) &&
 	    __skb_linearize(skb))
@@ -1290,12 +1409,13 @@ int dev_queue_xmit(struct sk_buff *skb)
 	      	if (skb_checksum_help(skb, 0))
 	      		goto out_kfree_skb;
 
+gso:
 	spin_lock_prefetch(&dev->queue_lock);
 
 	/* Disable soft irqs for various locks below. Also 
 	 * stops preemption for RCU. 
 	 */
-	local_bh_disable(); 
+	rcu_read_lock_bh(); 
 
 	/* Updates of qdisc are serialized by queue_lock. 
 	 * The struct Qdisc which is pointed to by qdisc is now a 
@@ -1346,11 +1466,8 @@ int dev_queue_xmit(struct sk_buff *skb)
 			HARD_TX_LOCK(dev, cpu);
 
 			if (!netif_queue_stopped(dev)) {
-				if (netdev_nit)
-					dev_queue_xmit_nit(skb, dev);
-
 				rc = 0;
-				if (!dev->hard_start_xmit(skb, dev)) {
+				if (!dev_hard_start_xmit(skb, dev)) {
 					HARD_TX_UNLOCK(dev);
 					goto out;
 				}
@@ -1369,13 +1486,13 @@ int dev_queue_xmit(struct sk_buff *skb)
 	}
 
 	rc = -ENETDOWN;
-	local_bh_enable();
+	rcu_read_unlock_bh();
 
 out_kfree_skb:
 	kfree_skb(skb);
 	return rc;
 out:
-	local_bh_enable();
+	rcu_read_unlock_bh();
 	return rc;
 }
 
@@ -3301,8 +3418,8 @@ static void net_dma_rebalance(void)
 /**
  * netdev_dma_event - event callback for the net_dma_client
  * @client: should always be net_dma_client
- * @chan:
- * @event:
+ * @chan: DMA channel for the event
+ * @event: event type
  */
 static void netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
 	enum dma_event event)
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 33ce7ed6afc..27ce1683caf 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -614,6 +614,29 @@ static int ethtool_set_ufo(struct net_device *dev, char __user *useraddr)
 	return dev->ethtool_ops->set_ufo(dev, edata.data);
 }
 
+static int ethtool_get_gso(struct net_device *dev, char __user *useraddr)
+{
+	struct ethtool_value edata = { ETHTOOL_GGSO };
+
+	edata.data = dev->features & NETIF_F_GSO;
+	if (copy_to_user(useraddr, &edata, sizeof(edata)))
+		 return -EFAULT;
+	return 0;
+}
+
+static int ethtool_set_gso(struct net_device *dev, char __user *useraddr)
+{
+	struct ethtool_value edata;
+
+	if (copy_from_user(&edata, useraddr, sizeof(edata)))
+		return -EFAULT;
+	if (edata.data)
+		dev->features |= NETIF_F_GSO;
+	else
+		dev->features &= ~NETIF_F_GSO;
+	return 0;
+}
+
 static int ethtool_self_test(struct net_device *dev, char __user *useraddr)
 {
 	struct ethtool_test test;
@@ -905,6 +928,12 @@ int dev_ethtool(struct ifreq *ifr)
 	case ETHTOOL_SUFO:
 		rc = ethtool_set_ufo(dev, useraddr);
 		break;
+	case ETHTOOL_GGSO:
+		rc = ethtool_get_gso(dev, useraddr);
+		break;
+	case ETHTOOL_SGSO:
+		rc = ethtool_set_gso(dev, useraddr);
+		break;
 	default:
 		rc =  -EOPNOTSUPP;
 	}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index bb7210f4005..8e5044ba3ab 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -172,9 +172,9 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 	shinfo = skb_shinfo(skb);
 	atomic_set(&shinfo->dataref, 1);
 	shinfo->nr_frags  = 0;
-	shinfo->tso_size = 0;
-	shinfo->tso_segs = 0;
-	shinfo->ufo_size = 0;
+	shinfo->gso_size = 0;
+	shinfo->gso_segs = 0;
+	shinfo->gso_type = 0;
 	shinfo->ip6_frag_id = 0;
 	shinfo->frag_list = NULL;
 
@@ -238,8 +238,9 @@ struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp,
 
 	atomic_set(&(skb_shinfo(skb)->dataref), 1);
 	skb_shinfo(skb)->nr_frags  = 0;
-	skb_shinfo(skb)->tso_size = 0;
-	skb_shinfo(skb)->tso_segs = 0;
+	skb_shinfo(skb)->gso_size = 0;
+	skb_shinfo(skb)->gso_segs = 0;
+	skb_shinfo(skb)->gso_type = 0;
 	skb_shinfo(skb)->frag_list = NULL;
 out:
 	return skb;
@@ -528,8 +529,9 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 #endif
 	skb_copy_secmark(new, old);
 	atomic_set(&new->users, 1);
-	skb_shinfo(new)->tso_size = skb_shinfo(old)->tso_size;
-	skb_shinfo(new)->tso_segs = skb_shinfo(old)->tso_segs;
+	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;
 }
 
 /**
@@ -781,24 +783,40 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
  *	filled. Used by network drivers which may DMA or transfer data
  *	beyond the buffer end onto the wire.
  *
- *	May return NULL in out of memory cases.
+ *	May return error in out of memory cases. The skb is freed on error.
  */
  
-struct sk_buff *skb_pad(struct sk_buff *skb, int pad)
+int skb_pad(struct sk_buff *skb, int pad)
 {
-	struct sk_buff *nskb;
+	int err;
+	int ntail;
 	
 	/* If the skbuff is non linear tailroom is always zero.. */
-	if (skb_tailroom(skb) >= pad) {
+	if (!skb_cloned(skb) && skb_tailroom(skb) >= pad) {
 		memset(skb->data+skb->len, 0, pad);
-		return skb;
+		return 0;
 	}
-	
-	nskb = skb_copy_expand(skb, skb_headroom(skb), skb_tailroom(skb) + pad, GFP_ATOMIC);
+
+	ntail = skb->data_len + pad - (skb->end - skb->tail);
+	if (likely(skb_cloned(skb) || ntail > 0)) {
+		err = pskb_expand_head(skb, 0, ntail, GFP_ATOMIC);
+		if (unlikely(err))
+			goto free_skb;
+	}
+
+	/* FIXME: The use of this function with non-linear skb's really needs
+	 * to be audited.
+	 */
+	err = skb_linearize(skb);
+	if (unlikely(err))
+		goto free_skb;
+
+	memset(skb->data + skb->len, 0, pad);
+	return 0;
+
+free_skb:
 	kfree_skb(skb);
-	if (nskb)
-		memset(nskb->data+nskb->len, 0, pad);
-	return nskb;
+	return err;
 }	
  
 /* Trims skb to length len. It can change skb pointers.
@@ -1824,6 +1842,132 @@ unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
 
 EXPORT_SYMBOL_GPL(skb_pull_rcsum);
 
+/**
+ *	skb_segment - Perform protocol segmentation on skb.
+ *	@skb: buffer to segment
+ *	@sg: whether scatter-gather can be used for generated segments
+ *
+ *	This function performs segmentation on the given skb.  It returns
+ *	the segment at the given position.  It returns NULL if there are
+ *	no more segments to generate, or when an error is encountered.
+ */
+struct sk_buff *skb_segment(struct sk_buff *skb, int sg)
+{
+	struct sk_buff *segs = NULL;
+	struct sk_buff *tail = NULL;
+	unsigned int mss = skb_shinfo(skb)->gso_size;
+	unsigned int doffset = skb->data - skb->mac.raw;
+	unsigned int offset = doffset;
+	unsigned int headroom;
+	unsigned int len;
+	int nfrags = skb_shinfo(skb)->nr_frags;
+	int err = -ENOMEM;
+	int i = 0;
+	int pos;
+
+	__skb_push(skb, doffset);
+	headroom = skb_headroom(skb);
+	pos = skb_headlen(skb);
+
+	do {
+		struct sk_buff *nskb;
+		skb_frag_t *frag;
+		int hsize, nsize;
+		int k;
+		int size;
+
+		len = skb->len - offset;
+		if (len > mss)
+			len = mss;
+
+		hsize = skb_headlen(skb) - offset;
+		if (hsize < 0)
+			hsize = 0;
+		nsize = hsize + doffset;
+		if (nsize > len + doffset || !sg)
+			nsize = len + doffset;
+
+		nskb = alloc_skb(nsize + headroom, GFP_ATOMIC);
+		if (unlikely(!nskb))
+			goto err;
+
+		if (segs)
+			tail->next = nskb;
+		else
+			segs = nskb;
+		tail = nskb;
+
+		nskb->dev = skb->dev;
+		nskb->priority = skb->priority;
+		nskb->protocol = skb->protocol;
+		nskb->dst = dst_clone(skb->dst);
+		memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
+		nskb->pkt_type = skb->pkt_type;
+		nskb->mac_len = skb->mac_len;
+
+		skb_reserve(nskb, headroom);
+		nskb->mac.raw = nskb->data;
+		nskb->nh.raw = nskb->data + skb->mac_len;
+		nskb->h.raw = nskb->nh.raw + (skb->h.raw - skb->nh.raw);
+		memcpy(skb_put(nskb, doffset), skb->data, doffset);
+
+		if (!sg) {
+			nskb->csum = skb_copy_and_csum_bits(skb, offset,
+							    skb_put(nskb, len),
+							    len, 0);
+			continue;
+		}
+
+		frag = skb_shinfo(nskb)->frags;
+		k = 0;
+
+		nskb->ip_summed = CHECKSUM_HW;
+		nskb->csum = skb->csum;
+		memcpy(skb_put(nskb, hsize), skb->data + offset, hsize);
+
+		while (pos < offset + len) {
+			BUG_ON(i >= nfrags);
+
+			*frag = skb_shinfo(skb)->frags[i];
+			get_page(frag->page);
+			size = frag->size;
+
+			if (pos < offset) {
+				frag->page_offset += offset - pos;
+				frag->size -= offset - pos;
+			}
+
+			k++;
+
+			if (pos + size <= offset + len) {
+				i++;
+				pos += size;
+			} else {
+				frag->size -= pos + size - (offset + len);
+				break;
+			}
+
+			frag++;
+		}
+
+		skb_shinfo(nskb)->nr_frags = k;
+		nskb->data_len = len - hsize;
+		nskb->len += nskb->data_len;
+		nskb->truesize += nskb->data_len;
+	} while ((offset += len) < skb->len);
+
+	return segs;
+
+err:
+	while ((skb = segs)) {
+		segs = skb->next;
+		kfree(skb);
+	}
+	return ERR_PTR(err);
+}
+
+EXPORT_SYMBOL_GPL(skb_segment);
+
 void __init skb_init(void)
 {
 	skbuff_head_cache = kmem_cache_create("skbuff_head_cache",