Merge branch 'net-tso-expand-to-UDP-support'

Eric Dumazet says:

====================
net: tso: expand to UDP support

With QUIC getting more attention these days, it is worth
implementing UDP direct segmentation, the same we did for TCP.

Drivers will need to advertize NETIF_F_GSO_UDP_L4 so that
GSO stack does not do the (more expensive) segmentation.

Note the two first patches are stable candidates, after
tests confirm they do not add regressions.

v2: addressed Jakub feedback :
   1) Added a prep patch for octeontx2-af
   2) calls tso_start() earlier in otx2_sq_append_tso()
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/cavium/thunder/nicvf_queues.c

@@ -1489,9 +1489,10 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq,
 	int seg_subdescs = 0, desc_cnt = 0;
 	int seg_len, total_len, data_left;
 	int hdr_qentry = qentry;
-	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	int hdr_len;
+
+	hdr_len = tso_start(skb, &tso);
 
-	tso_start(skb, &tso);
 	total_len = skb->len - hdr_len;
 	while (total_len > 0) {
 		char *hdr;

drivers/net/ethernet/freescale/fec_main.c

@@ -710,8 +710,7 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 				   struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
-	int total_len, data_left;
+	int hdr_len, total_len, data_left;
 	struct bufdesc *bdp = txq->bd.cur;
 	struct tso_t tso;
 	unsigned int index = 0;
@@ -731,7 +730,7 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
 	}
 
 	/* Initialize the TSO handler, and prepare the first payload */
-	tso_start(skb, &tso);
+	hdr_len = tso_start(skb, &tso);
 
 	total_len = skb->len - hdr_len;
 	while (total_len > 0) {

drivers/net/ethernet/marvell/mv643xx_eth.c

@@ -816,10 +816,9 @@ static int txq_submit_tso(struct tx_queue *txq, struct sk_buff *skb,
 			  struct net_device *dev)
 {
 	struct mv643xx_eth_private *mp = txq_to_mp(txq);
-	int total_len, data_left, ret;
+	int hdr_len, total_len, data_left, ret;
 	int desc_count = 0;
 	struct tso_t tso;
-	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
 	struct tx_desc *first_tx_desc;
 	u32 first_cmd_sts = 0;
 
@@ -832,7 +831,7 @@ static int txq_submit_tso(struct tx_queue *txq, struct sk_buff *skb,
 	first_tx_desc = &txq->tx_desc_area[txq->tx_curr_desc];
 
 	/* Initialize the TSO handler, and prepare the first payload */
-	tso_start(skb, &tso);
+	hdr_len = tso_start(skb, &tso);
 
 	total_len = skb->len - hdr_len;
 	while (total_len > 0) {

drivers/net/ethernet/marvell/mvneta.c

@@ -2604,11 +2604,10 @@ mvneta_tso_put_data(struct net_device *dev, struct mvneta_tx_queue *txq,
 static int mvneta_tx_tso(struct sk_buff *skb, struct net_device *dev,
 			 struct mvneta_tx_queue *txq)
 {
-	int total_len, data_left;
+	int hdr_len, total_len, data_left;
 	int desc_count = 0;
 	struct mvneta_port *pp = netdev_priv(dev);
 	struct tso_t tso;
-	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
 	int i;
 
 	/* Count needed descriptors */
@@ -2621,7 +2620,7 @@ static int mvneta_tx_tso(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	/* Initialize the TSO handler, and prepare the first payload */
-	tso_start(skb, &tso);
+	hdr_len = tso_start(skb, &tso);
 
 	total_len = skb->len - hdr_len;
 	while (total_len > 0) {

drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c

@@ -3160,9 +3160,8 @@ static int mvpp2_tx_tso(struct sk_buff *skb, struct net_device *dev,
 			struct mvpp2_txq_pcpu *txq_pcpu)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
+	int hdr_sz, i, len, descs = 0;
 	struct tso_t tso;
-	int hdr_sz = skb_transport_offset(skb) + tcp_hdrlen(skb);
-	int i, len, descs = 0;
 
 	/* Check number of available descriptors */
 	if (mvpp2_aggr_desc_num_check(port, aggr_txq, tso_count_descs(skb)) ||
@@ -3170,7 +3169,8 @@ static int mvpp2_tx_tso(struct sk_buff *skb, struct net_device *dev,
 					     tso_count_descs(skb)))
 		return 0;
 
-	tso_start(skb, &tso);
+	hdr_sz = tso_start(skb, &tso);
+
 	len = skb->len - hdr_sz;
 	while (len > 0) {
 		int left = min_t(int, skb_shinfo(skb)->gso_size, len);

drivers/net/ethernet/marvell/octeontx2/af/common.h

@@ -43,7 +43,7 @@ struct qmem {
 	void            *base;
 	dma_addr_t	iova;
 	int		alloc_sz;
-	u8		entry_sz;
+	u16		entry_sz;
 	u8		align;
 	u32		qsize;
 };

drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c

@@ -619,13 +619,14 @@ static void otx2_sq_append_tso(struct otx2_nic *pfvf, struct otx2_snd_queue *sq,
 			       struct sk_buff *skb, u16 qidx)
 {
 	struct netdev_queue *txq = netdev_get_tx_queue(pfvf->netdev, qidx);
-	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
-	int tcp_data, seg_len, pkt_len, offset;
+	int hdr_len, tcp_data, seg_len, pkt_len, offset;
 	struct nix_sqe_hdr_s *sqe_hdr;
 	int first_sqe = sq->head;
 	struct sg_list list;
 	struct tso_t tso;
 
+	hdr_len = tso_start(skb, &tso);
+
 	/* Map SKB's fragments to DMA.
 	 * It's done here to avoid mapping for every TSO segment's packet.
 	 */
@@ -636,7 +637,6 @@ static void otx2_sq_append_tso(struct otx2_nic *pfvf, struct otx2_snd_queue *sq,
 
 	netdev_tx_sent_queue(txq, skb->len);
 
-	tso_start(skb, &tso);
 	tcp_data = skb->len - hdr_len;
 	while (tcp_data > 0) {
 		char *hdr;

include/net/tso.h

@@ -4,21 +4,22 @@
 
 #include <net/ip.h>
 
-#define TSO_HEADER_SIZE		128
+#define TSO_HEADER_SIZE		256
 
 struct tso_t {
-	int next_frag_idx;
-	void *data;
-	size_t size;
-	u16 ip_id;
-	bool ipv6;
-	u32 tcp_seq;
+	int	next_frag_idx;
+	int	size;
+	void	*data;
+	u16	ip_id;
+	u8	tlen; /* transport header len */
+	bool	ipv6;
+	u32	tcp_seq;
 };
 
-int tso_count_descs(struct sk_buff *skb);
-void tso_build_hdr(struct sk_buff *skb, char *hdr, struct tso_t *tso,
+int tso_count_descs(const struct sk_buff *skb);
+void tso_build_hdr(const struct sk_buff *skb, char *hdr, struct tso_t *tso,
 		   int size, bool is_last);
-void tso_build_data(struct sk_buff *skb, struct tso_t *tso, int size);
-void tso_start(struct sk_buff *skb, struct tso_t *tso);
+void tso_build_data(const struct sk_buff *skb, struct tso_t *tso, int size);
+int tso_start(struct sk_buff *skb, struct tso_t *tso);
 
 #endif	/* _TSO_H */

net/core/tso.c

@@ -6,18 +6,17 @@
 #include <asm/unaligned.h>
 
 /* Calculate expected number of TX descriptors */
-int tso_count_descs(struct sk_buff *skb)
+int tso_count_descs(const struct sk_buff *skb)
 {
 	/* The Marvell Way */
 	return skb_shinfo(skb)->gso_segs * 2 + skb_shinfo(skb)->nr_frags;
 }
 EXPORT_SYMBOL(tso_count_descs);
 
-void tso_build_hdr(struct sk_buff *skb, char *hdr, struct tso_t *tso,
+void tso_build_hdr(const struct sk_buff *skb, char *hdr, struct tso_t *tso,
 		   int size, bool is_last)
 {
-	struct tcphdr *tcph;
-	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	int hdr_len = skb_transport_offset(skb) + tso->tlen;
 	int mac_hdr_len = skb_network_offset(skb);
 
 	memcpy(hdr, skb->data, hdr_len);
@@ -30,23 +29,31 @@ void tso_build_hdr(struct sk_buff *skb, char *hdr, struct tso_t *tso,
 	} else {
 		struct ipv6hdr *iph = (void *)(hdr + mac_hdr_len);
 
-		iph->payload_len = htons(size + tcp_hdrlen(skb));
+		iph->payload_len = htons(size + tso->tlen);
 	}
-	tcph = (struct tcphdr *)(hdr + skb_transport_offset(skb));
-	put_unaligned_be32(tso->tcp_seq, &tcph->seq);
+	hdr += skb_transport_offset(skb);
+	if (tso->tlen != sizeof(struct udphdr)) {
+		struct tcphdr *tcph = (struct tcphdr *)hdr;
 
-	if (!is_last) {
-		/* Clear all special flags for not last packet */
-		tcph->psh = 0;
-		tcph->fin = 0;
-		tcph->rst = 0;
+		put_unaligned_be32(tso->tcp_seq, &tcph->seq);
+
+		if (!is_last) {
+			/* Clear all special flags for not last packet */
+			tcph->psh = 0;
+			tcph->fin = 0;
+			tcph->rst = 0;
+		}
+	} else {
+		struct udphdr *uh = (struct udphdr *)hdr;
+
+		uh->len = htons(sizeof(*uh) + size);
 	}
 }
 EXPORT_SYMBOL(tso_build_hdr);
 
-void tso_build_data(struct sk_buff *skb, struct tso_t *tso, int size)
+void tso_build_data(const struct sk_buff *skb, struct tso_t *tso, int size)
 {
-	tso->tcp_seq += size;
+	tso->tcp_seq += size; /* not worth avoiding this operation for UDP */
 	tso->size -= size;
 	tso->data += size;
 
@@ -62,12 +69,14 @@ void tso_build_data(struct sk_buff *skb, struct tso_t *tso, int size)
 }
 EXPORT_SYMBOL(tso_build_data);
 
-void tso_start(struct sk_buff *skb, struct tso_t *tso)
+int tso_start(struct sk_buff *skb, struct tso_t *tso)
 {
-	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	int tlen = skb_is_gso_tcp(skb) ? tcp_hdrlen(skb) : sizeof(struct udphdr);
+	int hdr_len = skb_transport_offset(skb) + tlen;
 
+	tso->tlen = tlen;
 	tso->ip_id = ntohs(ip_hdr(skb)->id);
-	tso->tcp_seq = ntohl(tcp_hdr(skb)->seq);
+	tso->tcp_seq = (tlen != sizeof(struct udphdr)) ? ntohl(tcp_hdr(skb)->seq) : 0;
 	tso->next_frag_idx = 0;
 	tso->ipv6 = vlan_get_protocol(skb) == htons(ETH_P_IPV6);
 
@@ -83,5 +92,6 @@ void tso_start(struct sk_buff *skb, struct tso_t *tso)
 		tso->data = skb_frag_address(frag);
 		tso->next_frag_idx++;
 	}
+	return hdr_len;
 }
 EXPORT_SYMBOL(tso_start);