tcp/lro: Allow drivers to set the TCP ACK/data segment aggregation limit

ACK aggregation limit is append count based, while the TCP data segment
aggregation limit is length based.  Unless the network driver sets these
two limits, it's an NO-OP.

Reviewed by:	adrian, gallatin (previous version), hselasky (previous version)
Approved by:	adrian (mentor)
MFC after:	1 week
Sponsored by:	Microsoft OSTC
Differential Revision:	https://reviews.freebsd.org/D5185

2 files changed, 18 insertions, 2 deletions

diff --git a/sys/netinet/tcp_lro.c b/sys/netinet/tcp_lro.c
index 62d8595..7067abe 100644
--- a/sys/netinet/tcp_lro.c
+++ b/sys/netinet/tcp_lro.c
@@ -88,6 +88,8 @@ tcp_lro_init_args(struct lro_ctrl *lc, struct ifnet *ifp,
 	lc->lro_mbuf_count = 0;
 	lc->lro_mbuf_max = lro_mbufs;
 	lc->lro_cnt = lro_entries;
+	lc->lro_ackcnt_lim = TCP_LRO_ACKCNT_MAX;
+	lc->lro_length_lim = TCP_LRO_LENGTH_MAX;
 	lc->ifp = ifp;
 	SLIST_INIT(&lc->lro_free);
 	SLIST_INIT(&lc->lro_active);
@@ -610,7 +612,7 @@ tcp_lro_rx(struct lro_ctrl *lc, struct mbuf *m, uint32_t csum)
 		}
 
 		/* Flush now if appending will result in overflow. */
-		if (le->p_len > (65535 - tcp_data_len)) {
+		if (le->p_len > (lc->lro_length_lim - tcp_data_len)) {
 			SLIST_REMOVE(&lc->lro_active, le, lro_entry, next);
 			tcp_lro_flush(lc, le);
 			break;
@@ -648,6 +650,15 @@ tcp_lro_rx(struct lro_ctrl *lc, struct mbuf *m, uint32_t csum)
 
 		if (tcp_data_len == 0) {
 			m_freem(m);
+			/*
+			 * Flush this LRO entry, if this ACK should not
+			 * be further delayed.
+			 */
+			if (le->append_cnt >= lc->lro_ackcnt_lim) {
+				SLIST_REMOVE(&lc->lro_active, le, lro_entry,
+				    next);
+				tcp_lro_flush(lc, le);
+			}
 			return (0);
 		}
 
@@ -668,7 +679,7 @@ tcp_lro_rx(struct lro_ctrl *lc, struct mbuf *m, uint32_t csum)
 		 * If a possible next full length packet would cause an
 		 * overflow, pro-actively flush now.
 		 */
-		if (le->p_len > (65535 - lc->ifp->if_mtu)) {
+		if (le->p_len > (lc->lro_length_lim - lc->ifp->if_mtu)) {
 			SLIST_REMOVE(&lc->lro_active, le, lro_entry, next);
 			tcp_lro_flush(lc, le);
 		} else
diff --git a/sys/netinet/tcp_lro.h b/sys/netinet/tcp_lro.h
index 48c679d..3fc627c 100644
--- a/sys/netinet/tcp_lro.h
+++ b/sys/netinet/tcp_lro.h
@@ -91,11 +91,16 @@ struct lro_ctrl {
 	unsigned	lro_cnt;
 	unsigned	lro_mbuf_count;
 	unsigned	lro_mbuf_max;
+	unsigned short	lro_ackcnt_lim;		/* max # of aggregated ACKs */
+	unsigned 	lro_length_lim;		/* max len of aggregated data */
 
 	struct lro_head	lro_active;
 	struct lro_head	lro_free;
 };
 
+#define	TCP_LRO_LENGTH_MAX	65535
+#define	TCP_LRO_ACKCNT_MAX	65535		/* unlimited */
+
 int tcp_lro_init(struct lro_ctrl *);
 int tcp_lro_init_args(struct lro_ctrl *, struct ifnet *, unsigned, unsigned);
 void tcp_lro_free(struct lro_ctrl *);