gro: Fix remcsum offload to deal with frags in GRO

The remote checksum offload GRO did not consider the case that frag0
might be in use. This patch fixes that by accessing headers using the
skb_gro functions and not saving offsets relative to skb->head.
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/vxlan.c

@@ -519,10 +519,10 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb,
 					  u32 data, struct gro_remcsum *grc,
 					  bool nopartial)
 {
-	size_t start, offset, plen;
+	size_t start, offset;
 
 	if (skb->remcsum_offload)
-		return NULL;
+		return vh;
 
 	if (!NAPI_GRO_CB(skb)->csum_valid)
 		return NULL;
@@ -532,17 +532,8 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb,
 			  offsetof(struct udphdr, check) :
 			  offsetof(struct tcphdr, check));
 
-	plen = hdrlen + offset + sizeof(u16);
-
-	/* Pull checksum that will be written */
-	if (skb_gro_header_hard(skb, off + plen)) {
-		vh = skb_gro_header_slow(skb, off + plen, off);
-		if (!vh)
-			return NULL;
-	}
-
-	skb_gro_remcsum_process(skb, (void *)vh + hdrlen,
-				start, offset, grc, nopartial);
+	vh = skb_gro_remcsum_process(skb, (void *)vh, off, hdrlen,
+				     start, offset, grc, nopartial);
 
 	skb->remcsum_offload = 1;
 
@@ -573,7 +564,6 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head,
 			goto out;
 	}
 
-	skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */
 	skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr));
 
 	flags = ntohl(vh->vx_flags);
@@ -588,6 +578,8 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head,
 			goto out;
 	}
 
+	skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */
+
 	flush = 0;
 
 	for (p = *head; p; p = p->next) {
@@ -1110,6 +1102,9 @@ static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh,
 {
 	size_t start, offset, plen;
 
+	if (skb->remcsum_offload)
+		return vh;
+
 	start = (data & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT;
 	offset = start + ((data & VXLAN_RCO_UDP) ?
 			  offsetof(struct udphdr, check) :

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,

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 @@ static int fou_gro_complete(struct sk_buff *skb, int nhoff,
 
 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;