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, 32 insertions, 12 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4bd177faa90c..6abe0d6f1e1d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2311,8 +2311,7 @@ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb);
 
 static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb)
 {
-	return (NAPI_GRO_CB(skb)->gro_remcsum_start - skb_headroom(skb) ==
-		skb_gro_offset(skb));
+	return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb));
 }
 
 static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb,
@@ -2408,37 +2407,58 @@ static inline void skb_gro_remcsum_init(struct gro_remcsum *grc)
 	grc->delta = 0;
 }
 
-static inline void skb_gro_remcsum_process(struct sk_buff *skb, void *ptr,
-					   int start, int offset,
-					   struct gro_remcsum *grc,
-					   bool nopartial)
+static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr,
+					    unsigned int off, size_t hdrlen,
+					    int start, int offset,
+					    struct gro_remcsum *grc,
+					    bool nopartial)
 {
 	__wsum delta;
+	size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start);
 
 	BUG_ON(!NAPI_GRO_CB(skb)->csum_valid);
 
 	if (!nopartial) {
-		NAPI_GRO_CB(skb)->gro_remcsum_start =
-		    ((unsigned char *)ptr + start) - skb->head;
-		return;
+		NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start;
+		return ptr;
+	}
+
+	ptr = skb_gro_header_fast(skb, off);
+	if (skb_gro_header_hard(skb, off + plen)) {
+		ptr = skb_gro_header_slow(skb, off + plen, off);
+		if (!ptr)
+			return NULL;
 	}
 
-	delta = remcsum_adjust(ptr, NAPI_GRO_CB(skb)->csum, start, offset);
+	delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum,
+			       start, offset);
 
 	/* Adjust skb->csum since we changed the packet */
 	NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta);
 
-	grc->offset = (ptr + offset) - (void *)skb->head;
+	grc->offset = off + hdrlen + offset;
 	grc->delta = delta;
+
+	return ptr;
 }
 
 static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb,
 					   struct gro_remcsum *grc)
 {
+	void *ptr;
+	size_t plen = grc->offset + sizeof(u16);
+
 	if (!grc->delta)
 		return;
 
-	remcsum_unadjust((__sum16 *)(skb->head + grc->offset), grc->delta);
+	ptr = skb_gro_header_fast(skb, grc->offset);
+	if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) {
+		ptr = skb_gro_header_slow(skb, plen, grc->offset);
+		if (!ptr)
+			return;
+	}
+
+	remcsum_unadjust((__sum16 *)ptr, grc->delta);
 }
 
 static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,