4 files changed, 185 insertions, 65 deletions

diff --git a/net/core/datagram.c b/net/core/datagram.c
index b01a76abe1d..22ea437c502 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -351,17 +351,111 @@ fault:
 }
 
 /**
+ *	skb_copy_datagram_const_iovec - Copy a datagram to an iovec.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying from
+ *	@to: io vector to copy to
+ *	@to_offset: offset in the io vector to start copying to
+ *	@len: amount of data to copy from buffer to iovec
+ *
+ *	Returns 0 or -EFAULT.
+ *	Note: the iovec is not modified during the copy.
+ */
+int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset,
+				  const struct iovec *to, int to_offset,
+				  int len)
+{
+	int start = skb_headlen(skb);
+	int i, copy = start - offset;
+
+	/* Copy header. */
+	if (copy > 0) {
+		if (copy > len)
+			copy = len;
+		if (memcpy_toiovecend(to, skb->data + offset, to_offset, copy))
+			goto fault;
+		if ((len -= copy) == 0)
+			return 0;
+		offset += copy;
+		to_offset += copy;
+	}
+
+	/* Copy paged appendix. Hmm... why does this look so complicated? */
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + skb_shinfo(skb)->frags[i].size;
+		if ((copy = end - offset) > 0) {
+			int err;
+			u8  *vaddr;
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+			struct page *page = frag->page;
+
+			if (copy > len)
+				copy = len;
+			vaddr = kmap(page);
+			err = memcpy_toiovecend(to, vaddr + frag->page_offset +
+						offset - start, to_offset, copy);
+			kunmap(page);
+			if (err)
+				goto fault;
+			if (!(len -= copy))
+				return 0;
+			offset += copy;
+			to_offset += copy;
+		}
+		start = end;
+	}
+
+	if (skb_shinfo(skb)->frag_list) {
+		struct sk_buff *list = skb_shinfo(skb)->frag_list;
+
+		for (; list; list = list->next) {
+			int end;
+
+			WARN_ON(start > offset + len);
+
+			end = start + list->len;
+			if ((copy = end - offset) > 0) {
+				if (copy > len)
+					copy = len;
+				if (skb_copy_datagram_const_iovec(list,
+							    offset - start,
+							    to, to_offset,
+							    copy))
+					goto fault;
+				if ((len -= copy) == 0)
+					return 0;
+				offset += copy;
+				to_offset += copy;
+			}
+			start = end;
+		}
+	}
+	if (!len)
+		return 0;
+
+fault:
+	return -EFAULT;
+}
+EXPORT_SYMBOL(skb_copy_datagram_const_iovec);
+
+/**
  *	skb_copy_datagram_from_iovec - Copy a datagram from an iovec.
  *	@skb: buffer to copy
  *	@offset: offset in the buffer to start copying to
  *	@from: io vector to copy to
+ *	@from_offset: offset in the io vector to start copying from
  *	@len: amount of data to copy to buffer from iovec
  *
  *	Returns 0 or -EFAULT.
- *	Note: the iovec is modified during the copy.
+ *	Note: the iovec is not modified during the copy.
  */
 int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
-				 struct iovec *from, int len)
+				 const struct iovec *from, int from_offset,
+				 int len)
 {
 	int start = skb_headlen(skb);
 	int i, copy = start - offset;
@@ -370,11 +464,12 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
-		if (memcpy_fromiovec(skb->data + offset, from, copy))
+		if (memcpy_fromiovecend(skb->data + offset, from, 0, copy))
 			goto fault;
 		if ((len -= copy) == 0)
 			return 0;
 		offset += copy;
+		from_offset += copy;
 	}
 
 	/* Copy paged appendix. Hmm... why does this look so complicated? */
@@ -393,8 +488,9 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
 			if (copy > len)
 				copy = len;
 			vaddr = kmap(page);
-			err = memcpy_fromiovec(vaddr + frag->page_offset +
-					       offset - start, from, copy);
+			err = memcpy_fromiovecend(vaddr + frag->page_offset +
+						  offset - start,
+						  from, from_offset, copy);
 			kunmap(page);
 			if (err)
 				goto fault;
@@ -402,6 +498,7 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
 			if (!(len -= copy))
 				return 0;
 			offset += copy;
+			from_offset += copy;
 		}
 		start = end;
 	}
@@ -420,11 +517,14 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
 					copy = len;
 				if (skb_copy_datagram_from_iovec(list,
 								 offset - start,
-								 from, copy))
+								 from,
+								 from_offset,
+								 copy))
 					goto fault;
 				if ((len -= copy) == 0)
 					return 0;
 				offset += copy;
+				from_offset += copy;
 			}
 			start = end;
 		}
diff --git a/net/core/dev.c b/net/core/dev.c
index 308a7d0c277..6785b067ad5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2378,18 +2378,13 @@ void *skb_gro_header(struct sk_buff *skb, unsigned int hlen)
 	unsigned int offset = skb_gro_offset(skb);
 
 	hlen += offset;
-	if (hlen <= skb_headlen(skb))
-		return skb->data + offset;
-
-	if (unlikely(!skb_shinfo(skb)->nr_frags ||
-		     skb_shinfo(skb)->frags[0].size <=
-		     hlen - skb_headlen(skb) ||
+	if (unlikely(skb_headlen(skb) ||
+		     skb_shinfo(skb)->frags[0].size < hlen ||
 		     PageHighMem(skb_shinfo(skb)->frags[0].page)))
 		return pskb_may_pull(skb, hlen) ? skb->data + offset : NULL;
 
 	return page_address(skb_shinfo(skb)->frags[0].page) +
-	       skb_shinfo(skb)->frags[0].page_offset +
-	       offset - skb_headlen(skb);
+	       skb_shinfo(skb)->frags[0].page_offset + offset;
 }
 EXPORT_SYMBOL(skb_gro_header);
 
@@ -2525,16 +2520,10 @@ void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(napi_reuse_skb);
 
-struct sk_buff *napi_fraginfo_skb(struct napi_struct *napi,
-				  struct napi_gro_fraginfo *info)
+struct sk_buff *napi_get_frags(struct napi_struct *napi)
 {
 	struct net_device *dev = napi->dev;
 	struct sk_buff *skb = napi->skb;
-	struct ethhdr *eth;
-	skb_frag_t *frag;
-	int i;
-
-	napi->skb = NULL;
 
 	if (!skb) {
 		skb = netdev_alloc_skb(dev, GRO_MAX_HEAD + NET_IP_ALIGN);
@@ -2542,47 +2531,14 @@ struct sk_buff *napi_fraginfo_skb(struct napi_struct *napi,
 			goto out;
 
 		skb_reserve(skb, NET_IP_ALIGN);
-	}
-
-	BUG_ON(info->nr_frags > MAX_SKB_FRAGS);
-	frag = info->frags;
 
-	for (i = 0; i < info->nr_frags; i++) {
-		skb_fill_page_desc(skb, i, frag->page, frag->page_offset,
-				   frag->size);
-		frag++;
-	}
-	skb_shinfo(skb)->nr_frags = info->nr_frags;
-
-	skb->data_len = info->len;
-	skb->len += info->len;
-	skb->truesize += info->len;
-
-	skb_reset_mac_header(skb);
-	skb_gro_reset_offset(skb);
-
-	eth = skb_gro_header(skb, sizeof(*eth));
-	if (!eth) {
-		napi_reuse_skb(napi, skb);
-		skb = NULL;
-		goto out;
+		napi->skb = skb;
 	}
 
-	skb_gro_pull(skb, sizeof(*eth));
-
-	/*
-	 * This works because the only protocols we care about don't require
-	 * special handling.  We'll fix it up properly at the end.
-	 */
-	skb->protocol = eth->h_proto;
-
-	skb->ip_summed = info->ip_summed;
-	skb->csum = info->csum;
-
 out:
 	return skb;
 }
-EXPORT_SYMBOL(napi_fraginfo_skb);
+EXPORT_SYMBOL(napi_get_frags);
 
 int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret)
 {
@@ -2612,9 +2568,39 @@ int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret)
 }
 EXPORT_SYMBOL(napi_frags_finish);
 
-int napi_gro_frags(struct napi_struct *napi, struct napi_gro_fraginfo *info)
+struct sk_buff *napi_frags_skb(struct napi_struct *napi)
+{
+	struct sk_buff *skb = napi->skb;
+	struct ethhdr *eth;
+
+	napi->skb = NULL;
+
+	skb_reset_mac_header(skb);
+	skb_gro_reset_offset(skb);
+
+	eth = skb_gro_header(skb, sizeof(*eth));
+	if (!eth) {
+		napi_reuse_skb(napi, skb);
+		skb = NULL;
+		goto out;
+	}
+
+	skb_gro_pull(skb, sizeof(*eth));
+
+	/*
+	 * This works because the only protocols we care about don't require
+	 * special handling.  We'll fix it up properly at the end.
+	 */
+	skb->protocol = eth->h_proto;
+
+out:
+	return skb;
+}
+EXPORT_SYMBOL(napi_frags_skb);
+
+int napi_gro_frags(struct napi_struct *napi)
 {
-	struct sk_buff *skb = napi_fraginfo_skb(napi, info);
+	struct sk_buff *skb = napi_frags_skb(napi);
 
 	if (!skb)
 		return NET_RX_DROP;
@@ -2718,7 +2704,7 @@ void netif_napi_del(struct napi_struct *napi)
 	struct sk_buff *skb, *next;
 
 	list_del_init(&napi->dev_list);
-	kfree_skb(napi->skb);
+	napi_free_frags(napi);
 
 	for (skb = napi->gro_list; skb; skb = next) {
 		next = skb->next;
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 9fd0dc3cca9..2797b711a97 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -51,7 +51,7 @@ static struct genl_family net_drop_monitor_family = {
 	.id             = GENL_ID_GENERATE,
 	.hdrsize        = 0,
 	.name           = "NET_DM",
-	.version        = 1,
+	.version        = 2,
 	.maxattr        = NET_DM_CMD_MAX,
 };
 
@@ -65,13 +65,17 @@ static void reset_per_cpu_data(struct per_cpu_dm_data *data)
 {
 	size_t al;
 	struct net_dm_alert_msg *msg;
+	struct nlattr *nla;
 
 	al = sizeof(struct net_dm_alert_msg);
 	al += dm_hit_limit * sizeof(struct net_dm_drop_point);
+	al += sizeof(struct nlattr);
+
 	data->skb = genlmsg_new(al, GFP_KERNEL);
 	genlmsg_put(data->skb, 0, 0, &net_drop_monitor_family,
 			0, NET_DM_CMD_ALERT);
-	msg = __nla_reserve_nohdr(data->skb, sizeof(struct net_dm_alert_msg));
+	nla = nla_reserve(data->skb, NLA_UNSPEC, sizeof(struct net_dm_alert_msg));
+	msg = nla_data(nla);
 	memset(msg, 0, al);
 	atomic_set(&data->dm_hit_count, dm_hit_limit);
 }
@@ -115,6 +119,7 @@ static void trace_kfree_skb_hit(struct sk_buff *skb, void *location)
 {
 	struct net_dm_alert_msg *msg;
 	struct nlmsghdr *nlh;
+	struct nlattr *nla;
 	int i;
 	struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
 
@@ -127,7 +132,8 @@ static void trace_kfree_skb_hit(struct sk_buff *skb, void *location)
 	}
 
 	nlh = (struct nlmsghdr *)data->skb->data;
-	msg = genlmsg_data(nlmsg_data(nlh));
+	nla = genlmsg_data(nlmsg_data(nlh));
+	msg = nla_data(nla);
 	for (i = 0; i < msg->entries; i++) {
 		if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) {
 			msg->points[i].count++;
@@ -139,6 +145,7 @@ static void trace_kfree_skb_hit(struct sk_buff *skb, void *location)
 	 * We need to create a new entry
 	 */
 	__nla_reserve_nohdr(data->skb, sizeof(struct net_dm_drop_point));
+	nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point));
 	memcpy(msg->points[msg->entries].pc, &location, sizeof(void *));
 	msg->points[msg->entries].count = 1;
 	msg->entries++;
diff --git a/net/core/iovec.c b/net/core/iovec.c
index 4c9c0121c9d..40a76ce19d9 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -98,6 +98,31 @@ int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len)
 }
 
 /*
+ *	Copy kernel to iovec. Returns -EFAULT on error.
+ */
+
+int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata,
+		      int offset, int len)
+{
+	int copy;
+	for (; len > 0; ++iov) {
+		/* Skip over the finished iovecs */
+		if (unlikely(offset >= iov->iov_len)) {
+			offset -= iov->iov_len;
+			continue;
+		}
+		copy = min_t(unsigned int, iov->iov_len - offset, len);
+		offset = 0;
+		if (copy_to_user(iov->iov_base, kdata, copy))
+			return -EFAULT;
+		kdata += copy;
+		len -= copy;
+	}
+
+	return 0;
+}
+
+/*
  *	Copy iovec to kernel. Returns -EFAULT on error.
  *
  *	Note: this modifies the original iovec.
@@ -122,10 +147,11 @@ int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len)
 }
 
 /*
- *	For use with ip_build_xmit
+ *	Copy iovec from kernel. Returns -EFAULT on error.
  */
-int memcpy_fromiovecend(unsigned char *kdata, struct iovec *iov, int offset,
-			int len)
+
+int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
+			int offset, int len)
 {
 	/* Skip over the finished iovecs */
 	while (offset >= iov->iov_len) {
@@ -236,3 +262,4 @@ EXPORT_SYMBOL(csum_partial_copy_fromiovecend);
 EXPORT_SYMBOL(memcpy_fromiovec);
 EXPORT_SYMBOL(memcpy_fromiovecend);
 EXPORT_SYMBOL(memcpy_toiovec);
+EXPORT_SYMBOL(memcpy_toiovecend);