Update frag_list in pskb_trim

[NET]: Update frag_list in pskb_trim

When pskb_trim has to defer to ___pksb_trim to trim the frag_list part of
the packet, the frag_list is not updated to reflect the trimming.  This
will usually work fine until you hit something that uses the packet length
or tail from the frag_list.

Examples include esp_output and ip_fragment.

Another problem caused by this is that you can end up with a linear packet
with a frag_list attached.

It is possible to get away with this if we audit everything to make sure
that they always consult skb->len before going down onto frag_list.  In
fact we can do the samething for the paged part as well to avoid copying
the data area of the skb.  For now though, let's do the conservative fix
and update frag_list.

Many thanks to Marco Berizzi for helping me to track down this bug.

This 4-year old bug took 3 months to track down.  Marco was very patient
indeed :)

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

1 files changed, 74 insertions, 32 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 0280535bdd5b..dd0ae1bd0742 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -251,11 +251,11 @@ nodata:
 }
 
 
-static void skb_drop_fraglist(struct sk_buff *skb)
+static void skb_drop_list(struct sk_buff **listp)
 {
-	struct sk_buff *list = skb_shinfo(skb)->frag_list;
+	struct sk_buff *list = *listp;
 
-	skb_shinfo(skb)->frag_list = NULL;
+	*listp = NULL;
 
 	do {
 		struct sk_buff *this = list;
@@ -264,6 +264,11 @@ static void skb_drop_fraglist(struct sk_buff *skb)
 	} while (list);
 }
 
+static inline void skb_drop_fraglist(struct sk_buff *skb)
+{
+	skb_drop_list(&skb_shinfo(skb)->frag_list);
+}
+
 static void skb_clone_fraglist(struct sk_buff *skb)
 {
 	struct sk_buff *list;
@@ -802,49 +807,86 @@ struct sk_buff *skb_pad(struct sk_buff *skb, int pad)
 	return nskb;
 }	
  
-/* Trims skb to length len. It can change skb pointers, if "realloc" is 1.
- * If realloc==0 and trimming is impossible without change of data,
- * it is BUG().
+/* Trims skb to length len. It can change skb pointers.
  */
 
-int ___pskb_trim(struct sk_buff *skb, unsigned int len, int realloc)
+int ___pskb_trim(struct sk_buff *skb, unsigned int len)
 {
+	struct sk_buff **fragp;
+	struct sk_buff *frag;
 	int offset = skb_headlen(skb);
 	int nfrags = skb_shinfo(skb)->nr_frags;
 	int i;
+	int err;
 
-	for (i = 0; i < nfrags; i++) {
+	if (skb_cloned(skb) &&
+	    unlikely((err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))))
+		return err;
+
+	i = 0;
+	if (offset >= len)
+		goto drop_pages;
+
+	for (; i < nfrags; i++) {
 		int end = offset + skb_shinfo(skb)->frags[i].size;
-		if (end > len) {
-			if (skb_cloned(skb)) {
-				BUG_ON(!realloc);
-				if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
-					return -ENOMEM;
-			}
-			if (len <= offset) {
-				put_page(skb_shinfo(skb)->frags[i].page);
-				skb_shinfo(skb)->nr_frags--;
-			} else {
-				skb_shinfo(skb)->frags[i].size = len - offset;
-			}
+
+		if (end < len) {
+			offset = end;
+			continue;
 		}
-		offset = end;
+
+		skb_shinfo(skb)->frags[i++].size = len - offset;
+
+drop_pages:
+		skb_shinfo(skb)->nr_frags = i;
+
+		for (; i < nfrags; i++)
+			put_page(skb_shinfo(skb)->frags[i].page);
+
+		if (skb_shinfo(skb)->frag_list)
+			skb_drop_fraglist(skb);
+		goto done;
+	}
+
+	for (fragp = &skb_shinfo(skb)->frag_list; (frag = *fragp);
+	     fragp = &frag->next) {
+		int end = offset + frag->len;
+
+		if (skb_shared(frag)) {
+			struct sk_buff *nfrag;
+
+			nfrag = skb_clone(frag, GFP_ATOMIC);
+			if (unlikely(!nfrag))
+				return -ENOMEM;
+
+			nfrag->next = frag->next;
+			kfree_skb(frag);
+			frag = nfrag;
+			*fragp = frag;
+		}
+
+		if (end < len) {
+			offset = end;
+			continue;
+		}
+
+		if (end > len &&
+		    unlikely((err = pskb_trim(frag, len - offset))))
+			return err;
+
+		if (frag->next)
+			skb_drop_list(&frag->next);
+		break;
 	}
 
-	if (offset < len) {
+done:
+	if (len > skb_headlen(skb)) {
 		skb->data_len -= skb->len - len;
 		skb->len       = len;
 	} else {
-		if (len <= skb_headlen(skb)) {
-			skb->len      = len;
-			skb->data_len = 0;
-			skb->tail     = skb->data + len;
-			if (skb_shinfo(skb)->frag_list && !skb_cloned(skb))
-				skb_drop_fraglist(skb);
-		} else {
-			skb->data_len -= skb->len - len;
-			skb->len       = len;
-		}
+		skb->len       = len;
+		skb->data_len  = 0;
+		skb->tail      = skb->data + len;
 	}
 
 	return 0;