skbuff: allow 'slow_gro' for skb carring sock reference

This change leverages the infrastructure introduced by the previous
patches to allow soft devices passing to the GRO engine owned skbs
without impacting the fast-path.

It's up to the GRO caller ensuring the slow_gro bit validity before
invoking the GRO engine. The new helper skb_prepare_for_gro() is
introduced for that goal.

On slow_gro, skbs are aggregated only with equal sk.
Additionally, skb truesize on GRO recycle and free is correctly
updated so that sk wmem is not changed by the GRO processing.

rfc-> v1:
 - fixed bad truesize on dev_gro_receive NAPI_FREE
 - use the existing state bit

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d04e286..fcbd977 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -958,6 +958,7 @@ void napi_skb_free_stolen_head(struct sk_buff *skb)
 		nf_reset_ct(skb);
 		skb_dst_drop(skb);
 		skb_ext_put(skb);
+		skb_orphan(skb);
 		skb->slow_gro = 0;
 	}
 	napi_skb_cache_put(skb);
@@ -3892,6 +3893,9 @@ int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb)
 	NAPI_GRO_CB(p)->last = skb;
 	NAPI_GRO_CB(p)->count++;
 	p->data_len += skb->len;
+
+	/* sk owenrship - if any - completely transferred to the aggregated packet */
+	skb->destructor = NULL;
 	p->truesize += skb->truesize;
 	p->len += skb->len;
 
@@ -4259,6 +4263,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 	unsigned int headlen = skb_headlen(skb);
 	unsigned int len = skb_gro_len(skb);
 	unsigned int delta_truesize;
+	unsigned int new_truesize;
 	struct sk_buff *lp;
 
 	if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush))
@@ -4290,10 +4295,10 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 		skb_frag_size_sub(frag, offset);
 
 		/* all fragments truesize : remove (head size + sk_buff) */
-		delta_truesize = skb->truesize -
-				 SKB_TRUESIZE(skb_end_offset(skb));
+		new_truesize = SKB_TRUESIZE(skb_end_offset(skb));
+		delta_truesize = skb->truesize - new_truesize;
 
-		skb->truesize -= skb->data_len;
+		skb->truesize = new_truesize;
 		skb->len -= skb->data_len;
 		skb->data_len = 0;
 
@@ -4322,12 +4327,16 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 		memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags);
 		/* We dont need to clear skbinfo->nr_frags here */
 
-		delta_truesize = skb->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff));
+		new_truesize = SKB_TRUESIZE(sizeof(struct sk_buff));
+		delta_truesize = skb->truesize - new_truesize;
+		skb->truesize = new_truesize;
 		NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD;
 		goto done;
 	}
 
 merge:
+	/* sk owenrship - if any - completely transferred to the aggregated packet */
+	skb->destructor = NULL;
 	delta_truesize = skb->truesize;
 	if (offset > headlen) {
 		unsigned int eat = offset - headlen;