Merge branch 'vlan-untag-and-insert-fixes'

Toshiaki Makita says:

====================
Fix vlan untag and insertion for bridge and vlan with reorder_hdr off

As Brandon Carpenter reported[1], sending non-vlan-offloaded packets from
bridge devices ends up with corrupted packets. He narrowed down this problem
and found that the root cause is in skb_reorder_vlan_header().

While I was working on fixing this problem, I found that the function does
not work properly for double tagged packets with reorder_hdr off as well.

Patch 1 fixes these 2 problems in skb_reorder_vlan_header().

And it turned out that fixing skb_reorder_vlan_header() is not sufficient
to receive double tagged packets with reorder_hdr off while I was testing the
fix. Vlan tags got out of order when vlan devices with reorder_hdr disabled
were stacked. Patch 2 fixes this problem.

[1] https://www.spinics.net/lists/linux-ethernet-bridging/msg07039.html
====================

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

include/linux/if_vlan.h

@@ -299,6 +299,44 @@ static inline bool vlan_hw_offload_capable(netdev_features_t features,
 	return false;
 }
 
+/**
+ * __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 error if skb_cow_head failes.
+ *
+ * Does not change skb->protocol so this function can be used during receive.
+ */
+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;
+
+	skb_push(skb, VLAN_HLEN);
+
+	/* 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;
+
+	/* now, the TCI */
+	veth->h_vlan_TCI = htons(vlan_tci);
+
+	return 0;
+}
+
 /**
  * __vlan_insert_tag - regular VLAN tag inserting
  * @skb: skbuff to tag
@@ -313,24 +351,37 @@ static inline bool vlan_hw_offload_capable(netdev_features_t features,
 static inline int __vlan_insert_tag(struct sk_buff *skb,
 				    __be16 vlan_proto, u16 vlan_tci)
 {
-	struct vlan_ethhdr *veth;
+	return __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN);
+}
 
-	if (skb_cow_head(skb, VLAN_HLEN) < 0)
-		return -ENOMEM;
+/**
+ * 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
+ * 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_inner_tag(struct sk_buff *skb,
+						    __be16 vlan_proto,
+						    u16 vlan_tci,
+						    unsigned int mac_len)
+{
+	int err;
 
-	veth = 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);
-	skb->mac_header -= VLAN_HLEN;
-
-	/* first, the ethernet type */
-	veth->h_vlan_proto = vlan_proto;
-
-	/* now, the TCI */
-	veth->h_vlan_TCI = htons(vlan_tci);
-
-	return 0;
+	err = __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, mac_len);
+	if (err) {
+		dev_kfree_skb_any(skb);
+		return NULL;
+	}
+	return skb;
 }
 
 /**
@@ -350,14 +401,7 @@ static inline int __vlan_insert_tag(struct sk_buff *skb,
 static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
 					      __be16 vlan_proto, u16 vlan_tci)
 {
-	int err;
-
-	err = __vlan_insert_tag(skb, vlan_proto, vlan_tci);
-	if (err) {
-		dev_kfree_skb_any(skb);
-		return NULL;
-	}
-	return skb;
+	return vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN);
 }
 
 /**

include/uapi/linux/if_ether.h

@@ -30,6 +30,7 @@
  */
 
 #define ETH_ALEN	6		/* Octets in one ethernet addr	 */
+#define ETH_TLEN	2		/* Octets in ethernet type field */
 #define ETH_HLEN	14		/* Total octets in header.	 */
 #define ETH_ZLEN	60		/* Min. octets in frame sans FCS */
 #define ETH_DATA_LEN	1500		/* Max. octets in payload	 */

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);

net/core/skbuff.c

@@ -5020,13 +5020,16 @@ EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len);
 
 static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 {
+	int mac_len;
+
 	if (skb_cow(skb, skb_headroom(skb)) < 0) {
 		kfree_skb(skb);
 		return NULL;
 	}
 
-	memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len - VLAN_HLEN,
-		2 * ETH_ALEN);
+	mac_len = skb->data - skb_mac_header(skb);
+	memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb),
+		mac_len - VLAN_HLEN - ETH_TLEN);
 	skb->mac_header += VLAN_HLEN;
 	return skb;
 }