vlan: Fix out of order vlan headers with reorder header off

With reorder header off, received packets are untagged in skb_vlan_untag()
called from within __netif_receive_skb_core(), and later the tag will be
inserted back in vlan_do_receive().

This caused out of order vlan headers when we create a vlan device on top
of another vlan device, because vlan_do_receive() inserts a tag as the
outermost vlan tag. E.g. the outer tag is first removed in skb_vlan_untag()
and inserted back in vlan_do_receive(), then the inner tag is next removed
and inserted back as the outermost tag.

This patch fixes the behaviour by inserting the inner tag at the right
position.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/if_vlan.h

@@ -300,30 +300,34 @@ static inline bool vlan_hw_offload_capable(netdev_features_t features,
 }
 
 /**
- * __vlan_insert_tag - regular VLAN tag inserting
+ * __vlan_insert_inner_tag - inner VLAN tag inserting
  * @skb: skbuff to tag
  * @vlan_proto: VLAN encapsulation protocol
  * @vlan_tci: VLAN TCI to insert
+ * @mac_len: MAC header length including outer vlan headers
  *
- * Inserts the VLAN tag into @skb as part of the payload
+ * Inserts the VLAN tag into @skb as part of the payload at offset mac_len
  * Returns error if skb_cow_head failes.
  *
  * Does not change skb->protocol so this function can be used during receive.
  */
-static inline int __vlan_insert_tag(struct sk_buff *skb,
-				    __be16 vlan_proto, u16 vlan_tci)
+static inline int __vlan_insert_inner_tag(struct sk_buff *skb,
+					  __be16 vlan_proto, u16 vlan_tci,
+					  unsigned int mac_len)
 {
 	struct vlan_ethhdr *veth;
 
 	if (skb_cow_head(skb, VLAN_HLEN) < 0)
 		return -ENOMEM;
 
-	veth = skb_push(skb, VLAN_HLEN);
+	skb_push(skb, VLAN_HLEN);
 
-	/* Move the mac addresses to the beginning of the new header. */
-	memmove(skb->data, skb->data + VLAN_HLEN, 2 * ETH_ALEN);
+	/* Move the mac header sans proto to the beginning of the new header. */
+	memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN);
 	skb->mac_header -= VLAN_HLEN;
 
+	veth = (struct vlan_ethhdr *)(skb->data + mac_len - ETH_HLEN);
+
 	/* first, the ethernet type */
 	veth->h_vlan_proto = vlan_proto;
 
@@ -334,12 +338,30 @@ static inline int __vlan_insert_tag(struct sk_buff *skb,
 }
 
 /**
- * vlan_insert_tag - regular VLAN tag inserting
+ * __vlan_insert_tag - regular VLAN tag inserting
  * @skb: skbuff to tag
  * @vlan_proto: VLAN encapsulation protocol
  * @vlan_tci: VLAN TCI to insert
  *
  * Inserts the VLAN tag into @skb as part of the payload
+ * Returns error if skb_cow_head failes.
+ *
+ * Does not change skb->protocol so this function can be used during receive.
+ */
+static inline int __vlan_insert_tag(struct sk_buff *skb,
+				    __be16 vlan_proto, u16 vlan_tci)
+{
+	return __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN);
+}
+
+/**
+ * vlan_insert_inner_tag - inner VLAN tag inserting
+ * @skb: skbuff to tag
+ * @vlan_proto: VLAN encapsulation protocol
+ * @vlan_tci: VLAN TCI to insert
+ * @mac_len: MAC header length including outer vlan headers
+ *
+ * Inserts the VLAN tag into @skb as part of the payload at offset mac_len
  * Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
  *
  * Following the skb_unshare() example, in case of error, the calling function
@@ -347,12 +369,14 @@ static inline int __vlan_insert_tag(struct sk_buff *skb,
  *
  * Does not change skb->protocol so this function can be used during receive.
  */
-static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
-					      __be16 vlan_proto, u16 vlan_tci)
+static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb,
+						    __be16 vlan_proto,
+						    u16 vlan_tci,
+						    unsigned int mac_len)
 {
 	int err;
 
-	err = __vlan_insert_tag(skb, vlan_proto, vlan_tci);
+	err = __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, mac_len);
 	if (err) {
 		dev_kfree_skb_any(skb);
 		return NULL;
@@ -360,6 +384,26 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
 	return skb;
 }
 
+/**
+ * vlan_insert_tag - regular VLAN tag inserting
+ * @skb: skbuff to tag
+ * @vlan_proto: VLAN encapsulation protocol
+ * @vlan_tci: VLAN TCI to insert
+ *
+ * Inserts the VLAN tag into @skb as part of the payload
+ * Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
+ *
+ * Following the skb_unshare() example, in case of error, the calling function
+ * doesn't have to worry about freeing the original skb.
+ *
+ * Does not change skb->protocol so this function can be used during receive.
+ */
+static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
+					      __be16 vlan_proto, u16 vlan_tci)
+{
+	return vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN);
+}
+
 /**
  * vlan_insert_tag_set_proto - regular VLAN tag inserting
  * @skb: skbuff to tag

net/8021q/vlan_core.c

@@ -48,8 +48,8 @@ bool vlan_do_receive(struct sk_buff **skbp)
 		 * original position later
 		 */
 		skb_push(skb, offset);
-		skb = *skbp = vlan_insert_tag(skb, skb->vlan_proto,
-					      skb->vlan_tci);
+		skb = *skbp = vlan_insert_inner_tag(skb, skb->vlan_proto,
+						    skb->vlan_tci, skb->mac_len);
 		if (!skb)
 			return false;
 		skb_pull(skb, offset + VLAN_HLEN);