Merge branch 'variable-length-ll-headers'

Willem de Bruijn says:

====================
net: validate variable length ll headers

Allow device-specific validation of link layer headers. Existing
checks drop all packets shorter than hard_header_len. For variable
length protocols, such packets can be valid.

patch 1 adds header_ops.validate and dev_validate_header
patch 2 implements the protocol specific callback for AX25
patch 3 replaces ll_header_truncated with dev_validate_header
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netdevice.h

@@ -268,6 +268,7 @@ struct header_ops {
 	void	(*cache_update)(struct hh_cache *hh,
 				const struct net_device *dev,
 				const unsigned char *haddr);
+	bool	(*validate)(const char *ll_header, unsigned int len);
 };
 
 /* These flag bits are private to the generic network queueing
@@ -1459,8 +1460,7 @@ enum netdev_priv_flags {
  *	@dma:		DMA channel
  *	@mtu:		Interface MTU value
  *	@type:		Interface hardware type
- *	@hard_header_len: Hardware header length, which means that this is the
- *			  minimum size of a packet.
+ *	@hard_header_len: Maximum hardware header length.
  *
  *	@needed_headroom: Extra headroom the hardware may need, but not in all
  *			  cases can this be guaranteed
@@ -2687,6 +2687,24 @@ static inline int dev_parse_header(const struct sk_buff *skb,
 	return dev->header_ops->parse(skb, haddr);
 }
 
+/* ll_header must have at least hard_header_len allocated */
+static inline bool dev_validate_header(const struct net_device *dev,
+				       char *ll_header, int len)
+{
+	if (likely(len >= dev->hard_header_len))
+		return true;
+
+	if (capable(CAP_SYS_RAWIO)) {
+		memset(ll_header + len, 0, dev->hard_header_len - len);
+		return true;
+	}
+
+	if (dev->header_ops && dev->header_ops->validate)
+		return dev->header_ops->validate(ll_header, len);
+
+	return false;
+}
+
 typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
 int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
 static inline int unregister_gifconf(unsigned int family)

net/ax25/ax25_ip.c

@@ -228,8 +228,23 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb)
 }
 #endif
 
+static bool ax25_validate_header(const char *header, unsigned int len)
+{
+	ax25_digi digi;
+
+	if (!len)
+		return false;
+
+	if (header[0])
+		return true;
+
+	return ax25_addr_parse(header + 1, len - 1, NULL, NULL, &digi, NULL,
+			       NULL);
+}
+
 const struct header_ops ax25_header_ops = {
 	.create = ax25_hard_header,
+	.validate = ax25_validate_header,
 };
 
 EXPORT_SYMBOL(ax25_header_ops);

net/packet/af_packet.c

@@ -1915,6 +1915,10 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg,
 		goto retry;
 	}
 
+	if (!dev_validate_header(dev, skb->data, len)) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
 	if (len > (dev->mtu + dev->hard_header_len + extra_len) &&
 	    !packet_extra_vlan_len_allowed(dev, skb)) {
 		err = -EMSGSIZE;
@@ -2393,18 +2397,6 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
-static bool ll_header_truncated(const struct net_device *dev, int len)
-{
-	/* net device doesn't like empty head */
-	if (unlikely(len < dev->hard_header_len)) {
-		net_warn_ratelimited("%s: packet size is too short (%d < %d)\n",
-				     current->comm, len, dev->hard_header_len);
-		return true;
-	}
-
-	return false;
-}
-
 static void tpacket_set_protocol(const struct net_device *dev,
 				 struct sk_buff *skb)
 {
@@ -2522,16 +2514,20 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		if (unlikely(err < 0))
 			return -EINVAL;
 	} else if (copylen) {
+		int hdrlen = min_t(int, copylen, tp_len);
+
 		skb_push(skb, dev->hard_header_len);
 		skb_put(skb, copylen - dev->hard_header_len);
-		err = skb_store_bits(skb, 0, data, copylen);
+		err = skb_store_bits(skb, 0, data, hdrlen);
 		if (unlikely(err))
 			return err;
+		if (!dev_validate_header(dev, skb->data, hdrlen))
+			return -EINVAL;
 		if (!skb->protocol)
 			tpacket_set_protocol(dev, skb);
 
-		data += copylen;
-		to_write -= copylen;
+		data += hdrlen;
+		to_write -= hdrlen;
 	}
 
 	offset = offset_in_page(data);
@@ -2703,13 +2699,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 			copylen = __virtio16_to_cpu(vio_le(),
 						    vnet_hdr->hdr_len);
 		}
-		if (dev->hard_header_len) {
-			if (ll_header_truncated(dev, tp_len)) {
-				tp_len = -EINVAL;
-				goto tpacket_error;
-			}
-			copylen = max_t(int, copylen, dev->hard_header_len);
-		}
+		copylen = max_t(int, copylen, dev->hard_header_len);
 		skb = sock_alloc_send_skb(&po->sk,
 				hlen + tlen + sizeof(struct sockaddr_ll) +
 				(copylen - dev->hard_header_len),
@@ -2905,16 +2895,19 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len);
 		if (unlikely(offset < 0))
 			goto out_free;
-	} else {
-		if (ll_header_truncated(dev, len))
-			goto out_free;
 	}
 
 	/* Returns -EFAULT on error */
 	err = skb_copy_datagram_from_iter(skb, offset, &msg->msg_iter, len);
 	if (err)
 		goto out_free;
 
+	if (sock->type == SOCK_RAW &&
+	    !dev_validate_header(dev, skb->data, len)) {
+		err = -EINVAL;
+		goto out_free;
+	}
+
 	sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
 
 	if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) &&