Merge branch 'gro_tunnels'

Tom Herbert says:

====================
gro: Fixes for tunnels and GRO

This patch set addresses some issue related to tunneling and GRO:

- Fix remote checksum offload to properly deal with frag0 in GRO.
- Add support for GRO at VXLAN tunnel (call gro_cells)

Testing: Ran one netperf TCP_STREAM to highlight impact of different
configurations:

GUE
  Zero UDP checksum
    4628.42 MBps
  UDP checksums enabled
    6800.51 MBps
  UDP checksums and remote checksum offload
    7663.82 MBps
  UDP checksums and remote checksum offload using no-partial
    7287.25 MBps

VXLAN
  Zero UDP checksum
    4112.02
  UDP checksums enabled
    6785.80 MBps
  UDP checksums and remote checksum offload
    7075.56 MBps

v2:
  - Drop "gro: Pull headers into skb head for 1st skb in gro list"
    from patch set
  - In vxlan_remcsum and gue_remcsum return immediately if remcsum
    processing was already done
  - Add gro callbacks for sit offload
  - Use WARN_ON_ONCE if we get a GUE protocol that does not have
    GRO offload support

v3:
  - Don't restore gro callbacks for sit offload
====================

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

1 files changed, 13 insertions, 17 deletions

diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 34968cd5c146..2d1646cff057 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -79,7 +79,11 @@ static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr,
 	__be16 *pd = data;
 	size_t start = ntohs(pd[0]);
 	size_t offset = ntohs(pd[1]);
-	size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start);
+	size_t plen = sizeof(struct udphdr) + hdrlen +
+	    max_t(size_t, offset + sizeof(u16), start);
+
+	if (skb->remcsum_offload)
+		return guehdr;
 
 	if (!pskb_may_pull(skb, plen))
 		return NULL;
@@ -221,29 +225,21 @@ out_unlock:
 
 static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
 				      struct guehdr *guehdr, void *data,
-				      size_t hdrlen, u8 ipproto,
-				      struct gro_remcsum *grc, bool nopartial)
+				      size_t hdrlen, struct gro_remcsum *grc,
+				      bool nopartial)
 {
 	__be16 *pd = data;
 	size_t start = ntohs(pd[0]);
 	size_t offset = ntohs(pd[1]);
-	size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start);
 
 	if (skb->remcsum_offload)
-		return NULL;
+		return guehdr;
 
 	if (!NAPI_GRO_CB(skb)->csum_valid)
 		return NULL;
 
-	/* Pull checksum that will be written */
-	if (skb_gro_header_hard(skb, off + plen)) {
-		guehdr = skb_gro_header_slow(skb, off + plen, off);
-		if (!guehdr)
-			return NULL;
-	}
-
-	skb_gro_remcsum_process(skb, (void *)guehdr + hdrlen,
-				start, offset, grc, nopartial);
+	guehdr = skb_gro_remcsum_process(skb, (void *)guehdr, off, hdrlen,
+					 start, offset, grc, nopartial);
 
 	skb->remcsum_offload = 1;
 
@@ -307,10 +303,10 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head,
 
 		if (flags & GUE_PFLAG_REMCSUM) {
 			guehdr = gue_gro_remcsum(skb, off, guehdr,
-						 data + doffset, hdrlen,
-						 guehdr->proto_ctype, &grc,
+						 data + doffset, hdrlen, &grc,
 						 !!(fou->flags &
 						    FOU_F_REMCSUM_NOPARTIAL));
+
 			if (!guehdr)
 				goto out;
 
@@ -351,7 +347,7 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head,
 	rcu_read_lock();
 	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
 	ops = rcu_dereference(offloads[guehdr->proto_ctype]);
-	if (WARN_ON(!ops || !ops->callbacks.gro_receive))
+	if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive))
 		goto out_unlock;
 
 	pp = ops->callbacks.gro_receive(head, skb);