gso: Support partial splitting at the frag_list pointer

klassert · davem330 · commit 07b26c9454a2 · 2016-09-19T20:59:34.000-04:00
Since commit 8a29111 ("net: gro: allow to build full sized skb") gro may build buffers with a frag_list. This can hurt forwarding because most NICs can't offload such packets, they need to be segmented in software. This patch splits buffers with a frag_list at the frag_list pointer into buffers that can be TSO offloaded. Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Acked-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
@@ -3097,18 +3097,39 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 	sg = !!(features & NETIF_F_SG);
 	csum = !!can_checksum_protocol(features, proto);
 
-	/* GSO partial only requires that we trim off any excess that
-	 * doesn't fit into an MSS sized block, so take care of that
-	 * now.
-	 */
-	if (sg && csum && (features & NETIF_F_GSO_PARTIAL)) {
+	if (sg && csum && (mss != GSO_BY_FRAGS))  {
+		if (!(features & NETIF_F_GSO_PARTIAL)) {
+			struct sk_buff *iter;
+
+			if (!list_skb ||
+			    !net_gso_ok(features, skb_shinfo(head_skb)->gso_type))
+				goto normal;
+
+			/* Split the buffer at the frag_list pointer.
+			 * This is based on the assumption that all
+			 * buffers in the chain excluding the last
+			 * containing the same amount of data.
+			 */
+			skb_walk_frags(head_skb, iter) {
+				if (skb_headlen(iter))
+					goto normal;
+
+				len -= iter->len;
+			}
+		}
+
+		/* GSO partial only requires that we trim off any excess that
+		 * doesn't fit into an MSS sized block, so take care of that
+		 * now.
+		 */
 		partial_segs = len / mss;
 		if (partial_segs > 1)
 			mss *= partial_segs;
 		else
 			partial_segs = 0;
 	}
 
+normal:
 	headroom = skb_headroom(head_skb);
 	pos = skb_headlen(head_skb);
 
@@ -3300,21 +3321,29 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 	 */
 	segs->prev = tail;
 
-	/* Update GSO info on first skb in partial sequence. */
 	if (partial_segs) {
+		struct sk_buff *iter;
 		int type = skb_shinfo(head_skb)->gso_type;
+		unsigned short gso_size = skb_shinfo(head_skb)->gso_size;
 
 		/* Update type to add partial and then remove dodgy if set */
-		type |= SKB_GSO_PARTIAL;
+		type |= (features & NETIF_F_GSO_PARTIAL) / NETIF_F_GSO_PARTIAL * SKB_GSO_PARTIAL;
 		type &= ~SKB_GSO_DODGY;
 
 		/* Update GSO info and prepare to start updating headers on
 		 * our way back down the stack of protocols.
 		 */
-		skb_shinfo(segs)->gso_size = skb_shinfo(head_skb)->gso_size;
-		skb_shinfo(segs)->gso_segs = partial_segs;
-		skb_shinfo(segs)->gso_type = type;
-		SKB_GSO_CB(segs)->data_offset = skb_headroom(segs) + doffset;
+		for (iter = segs; iter; iter = iter->next) {
+			skb_shinfo(iter)->gso_size = gso_size;
+			skb_shinfo(iter)->gso_segs = partial_segs;
+			skb_shinfo(iter)->gso_type = type;
+			SKB_GSO_CB(iter)->data_offset = skb_headroom(iter) + doffset;
+		}
+
+		if (tail->len - doffset <= gso_size)
+			skb_shinfo(tail)->gso_size = 0;
+		else if (tail != segs)
+			skb_shinfo(tail)->gso_segs = DIV_ROUND_UP(tail->len - doffset, gso_size);
 	}
 
 	/* Following permits correct backpressure, for protocols
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
@@ -1192,7 +1192,7 @@ EXPORT_SYMBOL(inet_sk_rebuild_header);
 struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 				 netdev_features_t features)
 {
-	bool udpfrag = false, fixedid = false, encap;
+	bool udpfrag = false, fixedid = false, gso_partial, encap;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	const struct net_offload *ops;
 	unsigned int offset = 0;
@@ -1245,6 +1245,8 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 	if (IS_ERR_OR_NULL(segs))
 		goto out;
 
+	gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
+
 	skb = segs;
 	do {
 		iph = (struct iphdr *)(skb_mac_header(skb) + nhoff);
@@ -1259,9 +1261,13 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 				iph->id = htons(id);
 				id += skb_shinfo(skb)->gso_segs;
 			}
-			tot_len = skb_shinfo(skb)->gso_size +
-				  SKB_GSO_CB(skb)->data_offset +
-				  skb->head - (unsigned char *)iph;
+
+			if (gso_partial)
+				tot_len = skb_shinfo(skb)->gso_size +
+					  SKB_GSO_CB(skb)->data_offset +
+					  skb->head - (unsigned char *)iph;
+			else
+				tot_len = skb->len - nhoff;
 		} else {
 			if (!fixedid)
 				iph->id = htons(id++);
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
@@ -24,7 +24,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	__be16 protocol = skb->protocol;
 	u16 mac_len = skb->mac_len;
 	int gre_offset, outer_hlen;
-	bool need_csum, ufo;
+	bool need_csum, ufo, gso_partial;
 
 	if (!skb->encapsulation)
 		goto out;
@@ -69,6 +69,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 		goto out;
 	}
 
+	gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
+
 	outer_hlen = skb_tnl_header_len(skb);
 	gre_offset = outer_hlen - tnl_hlen;
 	skb = segs;
@@ -96,7 +98,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 		greh = (struct gre_base_hdr *)skb_transport_header(skb);
 		pcsum = (__sum16 *)(greh + 1);
 
-		if (skb_is_gso(skb)) {
+		if (gso_partial) {
 			unsigned int partial_adj;
 
 			/* Adjust checksum to account for the fact that
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
@@ -90,12 +90,6 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 		goto out;
 	}
 
-	/* GSO partial only requires splitting the frame into an MSS
-	 * multiple and possibly a remainder.  So update the mss now.
-	 */
-	if (features & NETIF_F_GSO_PARTIAL)
-		mss = skb->len - (skb->len % mss);
-
 	copy_destructor = gso_skb->destructor == tcp_wfree;
 	ooo_okay = gso_skb->ooo_okay;
 	/* All segments but the first should have ooo_okay cleared */
@@ -108,6 +102,13 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	/* Only first segment might have ooo_okay set */
 	segs->ooo_okay = ooo_okay;
 
+	/* GSO partial and frag_list segmentation only requires splitting
+	 * the frame into an MSS multiple and possibly a remainder, both
+	 * cases return a GSO skb. So update the mss now.
+	 */
+	if (skb_is_gso(segs))
+		mss *= skb_shinfo(segs)->gso_segs;
+
 	delta = htonl(oldlen + (thlen + mss));
 
 	skb = segs;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
@@ -21,7 +21,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	__be16 new_protocol, bool is_ipv6)
 {
 	int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
-	bool remcsum, need_csum, offload_csum, ufo;
+	bool remcsum, need_csum, offload_csum, ufo, gso_partial;
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct udphdr *uh = udp_hdr(skb);
 	u16 mac_offset = skb->mac_header;
@@ -88,6 +88,8 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 		goto out;
 	}
 
+	gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
+
 	outer_hlen = skb_tnl_header_len(skb);
 	udp_offset = outer_hlen - tnl_hlen;
 	skb = segs;
@@ -117,7 +119,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 		 * will be using a length value equal to only one MSS sized
 		 * segment instead of the entire frame.
 		 */
-		if (skb_is_gso(skb)) {
+		if (gso_partial) {
 			uh->len = htons(skb_shinfo(skb)->gso_size +
 					SKB_GSO_CB(skb)->data_offset +
 					skb->head - (unsigned char *)uh);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
@@ -69,6 +69,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	int offset = 0;
 	bool encap, udpfrag;
 	int nhoff;
+	bool gso_partial;
 
 	skb_reset_network_header(skb);
 	nhoff = skb_network_header(skb) - skb_mac_header(skb);
@@ -101,9 +102,11 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	if (IS_ERR(segs))
 		goto out;
 
+	gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
+
 	for (skb = segs; skb; skb = skb->next) {
 		ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
-		if (skb_is_gso(skb))
+		if (gso_partial)
 			payload_len = skb_shinfo(skb)->gso_size +
 				      SKB_GSO_CB(skb)->data_offset +
 				      skb->head - (unsigned char *)(ipv6h + 1);
