- Switch the "net.inet.tcp.reass.cursegments" and

  "net.inet.tcp.reass.maxsegments" sysctl variables to be based on UMA zone
  stats. The value returned by the cursegments sysctl is approximate owing to
  the way in which uma_zone_get_cur is implemented.

- Discontinue use of V_tcp_reass_qsize as a global reassembly segment count
  variable in the reassembly implementation. The variable was used without
  proper synchronisation and was duplicating accounting done by UMA already. The
  lack of synchronisation was particularly problematic on SMP systems
  terminating many TCP sessions, resulting in poor TCP performance for
  connections with non-zero packet loss.

Sponsored by:	FreeBSD Foundation
Reviewed by:	andre, gnn, rpaulo (as part of a larger patch)
MFC after:	2 weeks

1 files changed, 23 insertions, 13 deletions

diff --git a/sys/netinet/tcp_reass.c b/sys/netinet/tcp_reass.c
index fb1430e..e361551 100644
--- a/sys/netinet/tcp_reass.c
+++ b/sys/netinet/tcp_reass.c
@@ -74,19 +74,22 @@ __FBSDID("$FreeBSD$");
 #include <netinet/tcp_debug.h>
 #endif /* TCPDEBUG */
 
+static int tcp_reass_sysctl_maxseg(SYSCTL_HANDLER_ARGS);
+static int tcp_reass_sysctl_qsize(SYSCTL_HANDLER_ARGS);
+
 SYSCTL_NODE(_net_inet_tcp, OID_AUTO, reass, CTLFLAG_RW, 0,
     "TCP Segment Reassembly Queue");
 
 static VNET_DEFINE(int, tcp_reass_maxseg) = 0;
 #define	V_tcp_reass_maxseg		VNET(tcp_reass_maxseg)
-SYSCTL_VNET_INT(_net_inet_tcp_reass, OID_AUTO, maxsegments, CTLFLAG_RDTUN,
-    &VNET_NAME(tcp_reass_maxseg), 0,
+SYSCTL_VNET_PROC(_net_inet_tcp_reass, OID_AUTO, maxsegments, CTLFLAG_RDTUN,
+    &VNET_NAME(tcp_reass_maxseg), 0, &tcp_reass_sysctl_maxseg, "I",
     "Global maximum number of TCP Segments in Reassembly Queue");
 
 static VNET_DEFINE(int, tcp_reass_qsize) = 0;
 #define	V_tcp_reass_qsize		VNET(tcp_reass_qsize)
-SYSCTL_VNET_INT(_net_inet_tcp_reass, OID_AUTO, cursegments, CTLFLAG_RD,
-    &VNET_NAME(tcp_reass_qsize), 0,
+SYSCTL_VNET_PROC(_net_inet_tcp_reass, OID_AUTO, cursegments, CTLFLAG_RD,
+    &VNET_NAME(tcp_reass_qsize), 0, &tcp_reass_sysctl_qsize, "I",
     "Global number of TCP Segments currently in Reassembly Queue");
 
 static VNET_DEFINE(int, tcp_reass_maxqlen) = 48;
@@ -148,7 +151,6 @@ tcp_reass_flush(struct tcpcb *tp)
 		m_freem(qe->tqe_m);
 		uma_zfree(V_tcp_reass_zone, qe);
 		tp->t_segqlen--;
-		V_tcp_reass_qsize--;
 	}
 
 	KASSERT((tp->t_segqlen == 0),
@@ -156,6 +158,20 @@ tcp_reass_flush(struct tcpcb *tp)
 	    tp, tp->t_segqlen));
 }
 
+static int
+tcp_reass_sysctl_maxseg(SYSCTL_HANDLER_ARGS)
+{
+	V_tcp_reass_maxseg = uma_zone_get_max(V_tcp_reass_zone);
+	return (sysctl_handle_int(oidp, arg1, arg2, req));
+}
+
+static int
+tcp_reass_sysctl_qsize(SYSCTL_HANDLER_ARGS)
+{
+	V_tcp_reass_qsize = uma_zone_get_cur(V_tcp_reass_zone);
+	return (sysctl_handle_int(oidp, arg1, arg2, req));
+}
+
 int
 tcp_reass(struct tcpcb *tp, struct tcphdr *th, int *tlenp, struct mbuf *m)
 {
@@ -184,12 +200,10 @@ tcp_reass(struct tcpcb *tp, struct tcphdr *th, int *tlenp, struct mbuf *m)
 	 * Limit the number of segments in the reassembly queue to prevent
 	 * holding on to too many segments (and thus running out of mbufs).
 	 * Make sure to let the missing segment through which caused this
-	 * queue.  Always keep one global queue entry spare to be able to
-	 * process the missing segment.
+	 * queue.
 	 */
 	if (th->th_seq != tp->rcv_nxt &&
-	    (V_tcp_reass_qsize + 1 >= V_tcp_reass_maxseg ||
-	     tp->t_segqlen >= V_tcp_reass_maxqlen)) {
+	    tp->t_segqlen >= V_tcp_reass_maxqlen) {
 		V_tcp_reass_overflows++;
 		TCPSTAT_INC(tcps_rcvmemdrop);
 		m_freem(m);
@@ -209,7 +223,6 @@ tcp_reass(struct tcpcb *tp, struct tcphdr *th, int *tlenp, struct mbuf *m)
 		return (0);
 	}
 	tp->t_segqlen++;
-	V_tcp_reass_qsize++;
 
 	/*
 	 * Find a segment which begins after this one does.
@@ -236,7 +249,6 @@ tcp_reass(struct tcpcb *tp, struct tcphdr *th, int *tlenp, struct mbuf *m)
 				m_freem(m);
 				uma_zfree(V_tcp_reass_zone, te);
 				tp->t_segqlen--;
-				V_tcp_reass_qsize--;
 				/*
 				 * Try to present any queued data
 				 * at the left window edge to the user.
@@ -273,7 +285,6 @@ tcp_reass(struct tcpcb *tp, struct tcphdr *th, int *tlenp, struct mbuf *m)
 		m_freem(q->tqe_m);
 		uma_zfree(V_tcp_reass_zone, q);
 		tp->t_segqlen--;
-		V_tcp_reass_qsize--;
 		q = nq;
 	}
 
@@ -310,7 +321,6 @@ present:
 			sbappendstream_locked(&so->so_rcv, q->tqe_m);
 		uma_zfree(V_tcp_reass_zone, q);
 		tp->t_segqlen--;
-		V_tcp_reass_qsize--;
 		q = nq;
 	} while (q && q->tqe_th->th_seq == tp->rcv_nxt);
 	ND6_HINT(tp);