udp: paged allocation with gso

When sending large datagrams that are later segmented, store data in
page frags to avoid copying from linear in skb_segment.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/ipv4/ip_output.c

@@ -878,11 +878,13 @@ static int __ip_append_data(struct sock *sk,
 	struct rtable *rt = (struct rtable *)cork->dst;
 	unsigned int wmem_alloc_delta = 0;
 	u32 tskey = 0;
+	bool paged;
 
 	skb = skb_peek_tail(queue);
 
 	exthdrlen = !skb ? rt->dst.header_len : 0;
 	mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize;
+	paged = !!cork->gso_size;
 
 	if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP &&
 	    sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
@@ -934,6 +936,7 @@ static int __ip_append_data(struct sock *sk,
 			unsigned int fraglen;
 			unsigned int fraggap;
 			unsigned int alloclen;
+			unsigned int pagedlen = 0;
 			struct sk_buff *skb_prev;
 alloc_new_skb:
 			skb_prev = skb;
@@ -954,8 +957,12 @@ alloc_new_skb:
 			if ((flags & MSG_MORE) &&
 			    !(rt->dst.dev->features&NETIF_F_SG))
 				alloclen = mtu;
-			else
+			else if (!paged)
 				alloclen = fraglen;
+			else {
+				alloclen = min_t(int, fraglen, MAX_HEADER);
+				pagedlen = fraglen - alloclen;
+			}
 
 			alloclen += exthdrlen;
 
@@ -999,7 +1006,7 @@ alloc_new_skb:
 			/*
 			 *	Find where to start putting bytes.
 			 */
-			data = skb_put(skb, fraglen + exthdrlen);
+			data = skb_put(skb, fraglen + exthdrlen - pagedlen);
 			skb_set_network_header(skb, exthdrlen);
 			skb->transport_header = (skb->network_header +
 						 fragheaderlen);
@@ -1015,7 +1022,7 @@ alloc_new_skb:
 				pskb_trim_unique(skb_prev, maxfraglen);
 			}
 
-			copy = datalen - transhdrlen - fraggap;
+			copy = datalen - transhdrlen - fraggap - pagedlen;
 			if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
 				err = -EFAULT;
 				kfree_skb(skb);
@@ -1023,7 +1030,7 @@ alloc_new_skb:
 			}
 
 			offset += copy;
-			length -= datalen - fraggap;
+			length -= copy + transhdrlen;
 			transhdrlen = 0;
 			exthdrlen = 0;
 			csummode = CHECKSUM_NONE;

net/ipv6/ip6_output.c

@@ -1276,6 +1276,7 @@ static int __ip6_append_data(struct sock *sk,
 	int csummode = CHECKSUM_NONE;
 	unsigned int maxnonfragsize, headersize;
 	unsigned int wmem_alloc_delta = 0;
+	bool paged;
 
 	skb = skb_peek_tail(queue);
 	if (!skb) {
@@ -1283,6 +1284,7 @@ static int __ip6_append_data(struct sock *sk,
 		dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len;
 	}
 
+	paged = !!cork->gso_size;
 	mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize;
 	orig_mtu = mtu;
 
@@ -1374,6 +1376,7 @@ emsgsize:
 			unsigned int fraglen;
 			unsigned int fraggap;
 			unsigned int alloclen;
+			unsigned int pagedlen = 0;
 alloc_new_skb:
 			/* There's no room in the current skb */
 			if (skb)
@@ -1396,11 +1399,17 @@ alloc_new_skb:
 
 			if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
 				datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
+			fraglen = datalen + fragheaderlen;
+
 			if ((flags & MSG_MORE) &&
 			    !(rt->dst.dev->features&NETIF_F_SG))
 				alloclen = mtu;
-			else
-				alloclen = datalen + fragheaderlen;
+			else if (!paged)
+				alloclen = fraglen;
+			else {
+				alloclen = min_t(int, fraglen, MAX_HEADER);
+				pagedlen = fraglen - alloclen;
+			}
 
 			alloclen += dst_exthdrlen;
 
@@ -1422,7 +1431,7 @@ alloc_new_skb:
 			 */
 			alloclen += sizeof(struct frag_hdr);
 
-			copy = datalen - transhdrlen - fraggap;
+			copy = datalen - transhdrlen - fraggap - pagedlen;
 			if (copy < 0) {
 				err = -EINVAL;
 				goto error;
@@ -1461,7 +1470,7 @@ alloc_new_skb:
 			/*
 			 *	Find where to start putting bytes
 			 */
-			data = skb_put(skb, fraglen);
+			data = skb_put(skb, fraglen - pagedlen);
 			skb_set_network_header(skb, exthdrlen);
 			data += fragheaderlen;
 			skb->transport_header = (skb->network_header +
@@ -1484,7 +1493,7 @@ alloc_new_skb:
 			}
 
 			offset += copy;
-			length -= datalen - fraggap;
+			length -= copy + transhdrlen;
 			transhdrlen = 0;
 			exthdrlen = 0;
 			dst_exthdrlen = 0;