Subject: keepalive per socket settings patch
To: None <tech-net@netbsd.org>
From: Christos Zoulas <christos@zoulas.com>
List: tech-net
Date: 06/19/2007 21:28:10
Hi,
This is pretty straight forward... The question is do we let setsockopt
specify arbitrary values, or do we cap them to the global settings like
I do now? Comments? If there are no disagreements I will commit this after
I write the documentation. If there are, speak now and I won't bother
with the docs.
christos
Index: tcp.h
===================================================================
RCS file: /cvsroot/src/sys/netinet/tcp.h,v
retrieving revision 1.25
diff -u -u -r1.25 tcp.h
--- tcp.h 9 Oct 2006 16:27:07 -0000 1.25
+++ tcp.h 20 Jun 2007 01:16:48 -0000
@@ -112,10 +112,19 @@
/*
* User-settable options (used with setsockopt).
*/
-#define TCP_NODELAY 0x01 /* don't delay send to coalesce packets */
-#define TCP_MAXSEG 0x02 /* set maximum segment size */
-/* Bits 0x04, 0x08 reserved for FreeBSD compatibility: TCP_NOPUSH, TCP_NOOPT */
-#define TCP_MD5SIG 0x10 /* use MD5 digests (RFC2385) */
+#define TCP_NODELAY 1 /* don't delay send to coalesce packets */
+#define TCP_MAXSEG 2 /* set maximum segment size */
+#define TCP_KEEPIDLE 3
+#ifdef notyet
+#define TCP_NOPUSH 4 /* reserved for FreeBSD compat */
+#endif
+#define TCP_KEEPINTVL 5
+#define TCP_KEEPCNT 6
+#define TCP_KEEPINIT 7
+#ifdef notyet
+#define TCP_NOOPT 8 /* reserved for FreeBSD compat */
+#endif
+#define TCP_MD5SIG 0x10 /* use MD5 digests (RFC2385) */
#define TCP_CONGCTL 0x20 /* selected congestion control */
#endif /* !_NETINET_TCP_H_ */
Index: tcp_input.c
===================================================================
RCS file: /cvsroot/src/sys/netinet/tcp_input.c,v
retrieving revision 1.266
diff -u -u -r1.266 tcp_input.c
--- tcp_input.c 18 May 2007 21:48:43 -0000 1.266
+++ tcp_input.c 20 Jun 2007 01:16:51 -0000
@@ -1606,7 +1606,7 @@
*/
tp->t_rcvtime = tcp_now;
if (TCPS_HAVEESTABLISHED(tp->t_state))
- TCP_TIMER_ARM(tp, TCPT_KEEP, tcp_keepidle);
+ TCP_TIMER_ARM(tp, TCPT_KEEP, tp->t_keepidle);
/*
* Process options.
@@ -2366,9 +2366,9 @@
*/
if (so->so_state & SS_CANTRCVMORE) {
soisdisconnected(so);
- if (tcp_maxidle > 0)
+ if (tp->t_maxidle > 0)
TCP_TIMER_ARM(tp, TCPT_2MSL,
- tcp_maxidle);
+ tp->t_maxidle);
}
tp->t_state = TCPS_FIN_WAIT_2;
}
@@ -3377,7 +3377,7 @@
* than the keep alive timer would allow, expire it.
*/
sc->sc_rxttot += sc->sc_rxtcur;
- if (sc->sc_rxttot >= TCPTV_KEEP_INIT)
+ if (sc->sc_rxttot >= tcp_keepinit)
goto dropit;
tcpstat.tcps_sc_retransmitted++;
@@ -3713,7 +3713,7 @@
tcp_sendseqinit(tp);
tcp_rcvseqinit(tp);
tp->t_state = TCPS_SYN_RECEIVED;
- TCP_TIMER_ARM(tp, TCPT_KEEP, TCPTV_KEEP_INIT);
+ TCP_TIMER_ARM(tp, TCPT_KEEP, tp->t_keepinit);
tcpstat.tcps_accepts++;
if ((sc->sc_flags & SCF_SACK_PERMIT) && tcp_do_sack)
Index: tcp_subr.c
===================================================================
RCS file: /cvsroot/src/sys/netinet/tcp_subr.c,v
retrieving revision 1.214
diff -u -u -r1.214 tcp_subr.c
--- tcp_subr.c 2 May 2007 20:40:25 -0000 1.214
+++ tcp_subr.c 20 Jun 2007 01:16:52 -0000
@@ -379,9 +379,6 @@
{
int hlen;
- /* Initialize the TCPCB template. */
- tcp_tcpcb_template();
-
in_pcbinit(&tcbtable, tcbhashsize, tcbhashsize);
hlen = sizeof(struct ip) + sizeof(struct tcphdr);
@@ -410,6 +407,9 @@
/* Initialize the congestion control algorithms. */
tcp_congctl_init();
+ /* Initialize the TCPCB template. */
+ tcp_tcpcb_template();
+
MOWNER_ATTACH(&tcp_tx_mowner);
MOWNER_ATTACH(&tcp_rx_mowner);
MOWNER_ATTACH(&tcp_reass_mowner);
@@ -976,6 +976,13 @@
tp->t_rttvar = tcp_rttdflt * PR_SLOWHZ << (TCP_RTTVAR_SHIFT + 2 - 1);
TCPT_RANGESET(tp->t_rxtcur, TCP_REXMTVAL(tp),
TCPTV_MIN, TCPTV_REXMTMAX);
+
+ /* Keep Alive */
+ tp->t_keepinit = tcp_keepinit;
+ tp->t_keepidle = tcp_keepidle;
+ tp->t_keepintvl = tcp_keepintvl;
+ tp->t_keepcnt = tcp_keepcnt;
+ tp->t_maxidle = tp->t_keepcnt * tp->t_keepintvl;
}
/*
@@ -1049,7 +1056,7 @@
tp->t_congctl = tcp_congctl_global;
tp->t_congctl->refcnt++;
-
+
return (tp);
}
@@ -2016,7 +2023,7 @@
#endif
tp->t_state = TCPS_ESTABLISHED;
- TCP_TIMER_ARM(tp, TCPT_KEEP, tcp_keepidle);
+ TCP_TIMER_ARM(tp, TCPT_KEEP, tp->t_keepidle);
#ifdef RTV_RPIPE
if (rt != NULL && rt->rt_rmx.rmx_recvpipe != 0)
Index: tcp_timer.c
===================================================================
RCS file: /cvsroot/src/sys/netinet/tcp_timer.c,v
retrieving revision 1.76
diff -u -u -r1.76 tcp_timer.c
--- tcp_timer.c 9 Oct 2006 16:27:07 -0000 1.76
+++ tcp_timer.c 20 Jun 2007 01:16:52 -0000
@@ -148,11 +148,12 @@
* Various tunable timer parameters. These are initialized in tcp_init(),
* unless they are patched.
*/
-int tcp_keepidle = 0;
-int tcp_keepintvl = 0;
-int tcp_keepcnt = 0; /* max idle probes */
+u_int tcp_keepinit = 0;
+u_int tcp_keepidle = 0;
+u_int tcp_keepintvl = 0;
+u_int tcp_keepcnt = 0; /* max idle probes */
+
int tcp_maxpersistidle = 0; /* max idle time in persist */
-int tcp_maxidle; /* computed in tcp_slowtimo() */
/*
* Time to delay the ACK. This is initialized in tcp_init(), unless
@@ -179,6 +180,9 @@
tcp_timer_init(void)
{
+ if (tcp_keepinit == 0)
+ tcp_keepinit = TCPTV_KEEP_INIT;
+
if (tcp_keepidle == 0)
tcp_keepidle = TCPTV_KEEP_IDLE;
@@ -251,7 +255,6 @@
int s;
s = splsoftnet();
- tcp_maxidle = tcp_keepcnt * tcp_keepintvl;
tcp_iss_seq += TCP_ISSINCR; /* increment iss */
tcp_now++; /* for timestamps */
splx(s);
@@ -542,9 +545,9 @@
KASSERT(so != NULL);
if (so->so_options & SO_KEEPALIVE &&
tp->t_state <= TCPS_CLOSE_WAIT) {
- if ((tcp_maxidle > 0) &&
+ if ((tp->t_maxidle > 0) &&
((tcp_now - tp->t_rcvtime) >=
- tcp_keepidle + tcp_maxidle))
+ tp->t_keepidle + tp->t_maxidle))
goto dropit;
/*
* Send a packet designed to force a response
@@ -572,9 +575,9 @@
(struct mbuf *)NULL, NULL, tp->rcv_nxt,
tp->snd_una - 1, 0);
}
- TCP_TIMER_ARM(tp, TCPT_KEEP, tcp_keepintvl);
+ TCP_TIMER_ARM(tp, TCPT_KEEP, tp->t_keepintvl);
} else
- TCP_TIMER_ARM(tp, TCPT_KEEP, tcp_keepidle);
+ TCP_TIMER_ARM(tp, TCPT_KEEP, tp->t_keepidle);
#ifdef TCP_DEBUG
if (tp && so->so_options & SO_DEBUG)
@@ -634,8 +637,9 @@
* control block. Otherwise, check again in a bit.
*/
if (tp->t_state != TCPS_TIME_WAIT &&
- ((tcp_maxidle == 0) || ((tcp_now - tp->t_rcvtime) <= tcp_maxidle)))
- TCP_TIMER_ARM(tp, TCPT_2MSL, tcp_keepintvl);
+ ((tp->t_maxidle == 0) ||
+ ((tcp_now - tp->t_rcvtime) <= tp->t_maxidle)))
+ TCP_TIMER_ARM(tp, TCPT_2MSL, tp->t_keepintvl);
else
tp = tcp_close(tp);
Index: tcp_timer.h
===================================================================
RCS file: /cvsroot/src/sys/netinet/tcp_timer.h,v
retrieving revision 1.24
diff -u -u -r1.24 tcp_timer.h
--- tcp_timer.h 26 Sep 2006 06:39:22 -0000 1.24
+++ tcp_timer.h 20 Jun 2007 01:16:52 -0000
@@ -182,11 +182,11 @@
extern const tcp_timer_func_t tcp_timer_funcs[TCPT_NTIMERS];
-extern int tcp_keepidle; /* time before keepalive probes begin */
-extern int tcp_keepintvl; /* time between keepalive probes */
-extern int tcp_keepcnt; /* number of keepalives, 0=infty */
+extern u_int tcp_keepinit; /* time before initial connection times out */
+extern u_int tcp_keepidle; /* time before keepalive probes begin */
+extern u_int tcp_keepintvl; /* time between keepalive probes */
+extern u_int tcp_keepcnt; /* number of keepalives, 0=infty */
extern int tcp_maxpersistidle; /* max idle time in persist */
-extern int tcp_maxidle; /* time to drop after starting probes */
extern int tcp_ttl; /* time to live for TCP segs */
extern const int tcp_backoff[];
Index: tcp_usrreq.c
===================================================================
RCS file: /cvsroot/src/sys/netinet/tcp_usrreq.c,v
retrieving revision 1.131
diff -u -u -r1.131 tcp_usrreq.c
--- tcp_usrreq.c 4 Mar 2007 06:03:22 -0000 1.131
+++ tcp_usrreq.c 20 Jun 2007 01:16:53 -0000
@@ -436,7 +436,7 @@
soisconnecting(so);
tcpstat.tcps_connattempt++;
tp->t_state = TCPS_SYN_SENT;
- TCP_TIMER_ARM(tp, TCPT_KEEP, TCPTV_KEEP_INIT);
+ TCP_TIMER_ARM(tp, TCPT_KEEP, tp->t_keepinit);
tp->iss = tcp_new_iss(tp, 0);
tcp_sendseqinit(tp);
error = tcp_output(tp);
@@ -614,6 +614,28 @@
return (error);
}
+static void
+change_keepalive(struct socket *so, struct tcpcb *tp)
+{
+ tp->t_maxidle = tp->t_keepcnt * tp->t_keepintvl;
+ TCP_TIMER_DISARM(tp, TCPT_KEEP);
+ TCP_TIMER_DISARM(tp, TCPT_2MSL);
+
+ if (tp->t_state == TCPS_SYN_RECEIVED ||
+ tp->t_state == TCPS_SYN_SENT) {
+ TCP_TIMER_ARM(tp, TCPT_KEEP, tp->t_keepinit);
+ } else if (so->so_options & SO_KEEPALIVE &&
+ tp->t_state <= TCPS_CLOSE_WAIT) {
+ TCP_TIMER_ARM(tp, TCPT_KEEP, tp->t_keepintvl);
+ } else {
+ TCP_TIMER_ARM(tp, TCPT_KEEP, tp->t_keepidle);
+ }
+
+ if ((tp->t_state == TCPS_FIN_WAIT_2) && (tp->t_maxidle > 0))
+ TCP_TIMER_ARM(tp, TCPT_2MSL, tp->t_maxidle);
+}
+
+
int
tcp_ctloutput(int op, struct socket *so, int level, int optname,
struct mbuf **mp)
@@ -715,7 +737,8 @@
break;
case TCP_MAXSEG:
- if (m && (i = *mtod(m, int *)) > 0 &&
+ if (m && m->m_len >= sizeof(int) &&
+ (i = *mtod(m, int *)) > 0 &&
i <= tp->t_peermss)
tp->t_peermss = i; /* limit on send size */
else
@@ -729,6 +752,46 @@
#endif
break;
+ case TCP_KEEPIDLE:
+ if (m && m->m_len >= sizeof(int) &&
+ (i = *mtod(m, int *)) >= 0 &&
+ i <= tcp_keepidle) {
+ tp->t_keepidle = i;
+ change_keepalive(so, tp);
+ } else
+ error = EINVAL;
+ break;
+
+ case TCP_KEEPINTVL:
+ if (m && m->m_len >= sizeof(int) &&
+ (i = *mtod(m, int *)) >= 0 &&
+ i <= tcp_keepintvl) {
+ tp->t_keepintvl = i;
+ change_keepalive(so, tp);
+ } else
+ error = EINVAL;
+ break;
+
+ case TCP_KEEPCNT:
+ if (m && m->m_len >= sizeof(int) &&
+ (i = *mtod(m, int *)) >= 0 &&
+ i <= tcp_keepcnt) {
+ tp->t_keepcnt = i;
+ change_keepalive(so, tp);
+ } else
+ error = EINVAL;
+ break;
+
+ case TCP_KEEPINIT:
+ if (m && m->m_len >= sizeof(int) &&
+ (i = *mtod(m, int *)) >= 0 &&
+ i <= tcp_keepinit) {
+ tp->t_keepinit = i;
+ change_keepalive(so, tp);
+ } else
+ error = EINVAL;
+ break;
+
default:
error = ENOPROTOOPT;
break;
@@ -944,8 +1007,8 @@
* a full close, we start a timer to make sure sockets are
* not left in FIN_WAIT_2 forever.
*/
- if ((tp->t_state == TCPS_FIN_WAIT_2) && (tcp_maxidle > 0))
- TCP_TIMER_ARM(tp, TCPT_2MSL, tcp_maxidle);
+ if ((tp->t_state == TCPS_FIN_WAIT_2) && (tp->t_maxidle > 0))
+ TCP_TIMER_ARM(tp, TCPT_2MSL, tp->t_maxidle);
}
return (tp);
}
@@ -1418,6 +1481,27 @@
return error;
}
+static int
+sysctl_tcp_keep(SYSCTLFN_ARGS)
+{
+ int error;
+ u_int tmp;
+ struct sysctlnode node;
+
+ node = *rnode;
+ tmp = *(u_int *)rnode->sysctl_data;
+ node.sysctl_data = &tmp;
+
+ error = sysctl_lookup(SYSCTLFN_CALL(&node));
+ if (error || newp == NULL)
+ return error;
+
+ *(u_int *)rnode->sysctl_data = tmp;
+ tcp_tcpcb_template(); /* update the template */
+ return 0;
+}
+
+
/*
* this (second stage) setup routine is a replacement for tcp_sysctl()
* (which is currently used for ipv4 and ipv6)
@@ -1585,19 +1669,19 @@
CTLTYPE_INT, "keepidle",
SYSCTL_DESCR("Allowed connection idle ticks before a "
"keepalive probe is sent"),
- NULL, 0, &tcp_keepidle, 0,
+ sysctl_tcp_keep, 0, &tcp_keepidle, 0,
CTL_NET, pf, IPPROTO_TCP, TCPCTL_KEEPIDLE, CTL_EOL);
sysctl_createv(clog, 0, NULL, NULL,
CTLFLAG_PERMANENT|CTLFLAG_READWRITE,
CTLTYPE_INT, "keepintvl",
SYSCTL_DESCR("Ticks before next keepalive probe is sent"),
- NULL, 0, &tcp_keepintvl, 0,
+ sysctl_tcp_keep, 0, &tcp_keepintvl, 0,
CTL_NET, pf, IPPROTO_TCP, TCPCTL_KEEPINTVL, CTL_EOL);
sysctl_createv(clog, 0, NULL, NULL,
CTLFLAG_PERMANENT|CTLFLAG_READWRITE,
CTLTYPE_INT, "keepcnt",
SYSCTL_DESCR("Number of keepalive probes to send"),
- NULL, 0, &tcp_keepcnt, 0,
+ sysctl_tcp_keep, 0, &tcp_keepcnt, 0,
CTL_NET, pf, IPPROTO_TCP, TCPCTL_KEEPCNT, CTL_EOL);
sysctl_createv(clog, 0, NULL, NULL,
CTLFLAG_PERMANENT|CTLFLAG_IMMEDIATE,
@@ -1658,6 +1742,12 @@
sysctl_inpcblist, 0, &tcbtable, 0,
CTL_NET, pf, IPPROTO_TCP, CTL_CREATE,
CTL_EOL);
+ sysctl_createv(clog, 0, NULL, NULL,
+ CTLFLAG_PERMANENT|CTLFLAG_READWRITE,
+ CTLTYPE_INT, "keepinit",
+ SYSCTL_DESCR("Ticks before initial tcp connection times out"),
+ sysctl_tcp_keep, 0, &tcp_keepinit, 0,
+ CTL_NET, pf, IPPROTO_TCP, CTL_CREATE, CTL_EOL);
/* ECN subtree */
sysctl_createv(clog, 0, NULL, &ecn_node,
Index: tcp_var.h
===================================================================
RCS file: /cvsroot/src/sys/netinet/tcp_var.h,v
retrieving revision 1.146
diff -u -u -r1.146 tcp_var.h
--- tcp_var.h 2 May 2007 20:40:25 -0000 1.146
+++ tcp_var.h 20 Jun 2007 01:16:54 -0000
@@ -331,6 +331,14 @@
uint8_t t_ecn_retries; /* # of ECN setup retries */
struct tcp_congctl *t_congctl; /* per TCB congctl algorithm */
+
+ /* Keepalive per socket */
+ u_int t_keepinit;
+ u_int t_keepidle;
+ u_int t_keepintvl;
+ u_int t_keepcnt;
+ u_int t_maxidle; /* t_keepcnt * t_keepintvl */
+
};
/*