[PATCH net-next RFC 8/8] udp: add gro

[Willem de Bruijn <willemdebruijn.kernel@gmail.com>]

From: Willem de Bruijn <willemb@google.com>

Very rough initial version of udp gro, for discussion purpose only at
this point.

Among others it
- lacks the cmsg UDP_SEGMENT to return gso_size
- probably breaks udp tunnels
- hard breaks at 40 segments
- does not allow a last segment of unequal size

Signed-off-by: Willem de Bruijn <willemb@google.com>
---
 include/uapi/linux/udp.h |  1 +
 net/ipv4/udp.c           | 71 ++++++++++++++++++++++++++++++++++++++++
 net/ipv4/udp_offload.c   | 11 +++----
 3 files changed, 76 insertions(+), 7 deletions(-)

diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h
index 09d00f8c442b..7fda3e8c7fcf 100644
--- a/include/uapi/linux/udp.h
+++ b/include/uapi/linux/udp.h
@@ -33,6 +33,7 @@ struct udphdr {
 #define UDP_NO_CHECK6_TX 101	/* Disable sending checksum for UDP6X */
 #define UDP_NO_CHECK6_RX 102	/* Disable accpeting checksum for UDP6 */
 #define UDP_SEGMENT	103	/* Set GSO segmentation size */
+#define UDP_GRO		104	/* Enable GRO */
 
 /* UDP encapsulation types */
 #define UDP_ENCAP_ESPINUDP_NON_IKE	1 /* draft-ietf-ipsec-nat-t-ike-00/01 */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index bd873a5b8a86..ae49c08e6225 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2387,6 +2387,51 @@ void udp_destroy_sock(struct sock *sk)
 	}
 }
 
+static struct sk_buff *udp_gro_receive_cb(struct sock *sk,
+					  struct list_head *head,
+					  struct sk_buff *skb)
+{
+	struct sk_buff *p;
+	unsigned int off;
+
+	off = skb_gro_offset(skb) - sizeof(struct udphdr);
+
+	list_for_each_entry(p, head, list) {
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		/* TODO: for UDP_GRO: match size unless last segment */
+		if (NAPI_GRO_CB(p)->flush)
+			break;
+
+		/* TODO: look into ip id check */
+		if (skb_gro_receive(p, skb)) {
+			NAPI_GRO_CB(skb)->flush = 1;
+			break;
+		}
+
+		if (NAPI_GRO_CB(skb)->count >= 40) {
+			return p;
+		}
+
+		return NULL;
+	}
+
+	return NULL;
+}
+
+static int udp_gro_complete_cb(struct sock *sk, struct sk_buff *skb,
+			       int nhoff)
+{
+	skb->csum_start = (unsigned char *)udp_hdr(skb) - skb->head;
+	skb->csum_offset = offsetof(struct udphdr, check);
+	skb->ip_summed = CHECKSUM_PARTIAL;
+
+	skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+
+	return 0;
+}
+
 /*
  *	Socket option code for UDP
  */
@@ -2450,6 +2495,32 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		up->gso_size = val;
 		break;
 
+	case UDP_GRO:
+	{
+		if (val < 0 || val > 1)
+			return -EINVAL;
+
+		lock_sock(sk);
+		if (val) {
+
+			if (!udp_sk(sk)->gro_receive) {
+				udp_sk(sk)->gro_complete = udp_gro_complete_cb;
+				udp_sk(sk)->gro_receive = udp_gro_receive_cb;
+			} else {
+				err = -EALREADY;
+			}
+		} else {
+			if (udp_sk(sk)->gro_receive) {
+				udp_sk(sk)->gro_receive = NULL;
+				udp_sk(sk)->gro_complete = NULL;
+			} else {
+				err = -ENOENT;
+			}
+		}
+		release_sock(sk);
+		break;
+	}
+
 	/*
 	 * 	UDP-Lite's partial checksum coverage (RFC 3828).
 	 */
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index f44fe328aa0f..6dd3f0a28b5e 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -386,6 +386,8 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 			NAPI_GRO_CB(p)->same_flow = 0;
 			continue;
 		}
+
+		/* TODO: for UDP_GRO: match size */
 	}
 
 	skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
@@ -437,11 +439,6 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff,
 
 	uh->len = newlen;
 
-	/* Set encapsulation before calling into inner gro_complete() functions
-	 * to make them set up the inner offsets.
-	 */
-	skb->encapsulation = 1;
-
 	rcu_read_lock();
 	sk = (*lookup)(skb, uh->source, uh->dest);
 	if (sk && udp_sk(sk)->gro_complete)
@@ -462,11 +459,11 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
 	if (uh->check) {
-		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4;
 		uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr,
 					  iph->daddr, 0);
 	} else {
-		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
+		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4;
 	}
 
 	return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb);
-- 
2.19.0.397.gdd90340f6a-goog