Date: Tue, 13 Apr 1999 10:44:08 -0400 From: Barry Lustig <barry@lustig.com> To: "David E. Cross" <crossd@cs.rpi.edu> Cc: freebsd-hackers@FreeBSD.ORG Subject: Re: ypserv Message-ID: <19990413144409.16671.qmail@devious.lustig.com> In-Reply-To: <199904122143.RAA25814@cs.rpi.edu> References: <199904122143.RAA25814@cs.rpi.edu>
index | next in thread | previous in thread | raw e-mail
David,
You need to compile ypserv with ElectricFence to start to track down this
problem. Otherwise, you don't see the problem until much later after the
problem really occurs.
I have a network with 3 2.x-stable machines running ypserv and 1
3.x-stable machine running ypserv. These machines serve yp to solaris 2.5.1,
2.6, 2.7, irix 5.3, 6.2, 6.3, 6.4, 6.5, and openstep 4.2 machines. I see
dozens of SEGV's from the ypserv processes on the FreeBSD boxes. Here is
what I managed to find. I was waiting for Bill Paul to get back to me on
this, but haven't heard from him.
Here is a stack trace from one of my cores:
(gdb) bt
#0 0x62ef in readtcp (xprt=0x20524fcc,
buf=0x2066b05c <Error reading address 0x2066b05c: Bad address>,
len=4000) at /usr/src/lib/libc/../libc/rpc/svc_tcp.c:346
#1 0xf103 in fill_input_buf (rstrm=0x204eefbc)
at /usr/src/lib/libc/../libc/xdr/xdr_rec.c:510
#2 0xf1ed in skip_input_bytes (rstrm=0x204eefbc, cnt=4)
at /usr/src/lib/libc/../libc/xdr/xdr_rec.c:576
#3 0xefd5 in xdrrec_eof (xdrs=0x204ece58)
at /usr/src/lib/libc/../libc/xdr/xdr_rec.c:436
#4 0x636d in svctcp_stat (xprt=0x20524fcc)
at /usr/src/lib/libc/../libc/rpc/svc_tcp.c:381
#5 0x7a0e in svc_getreqset (readfds=0xefbfd924)
at /usr/src/lib/libc/../libc/rpc/svc.c:480
#6 0x4241 in yp_svc_run () at /usr/src/usr.sbin/ypserv/yp_main.c:144
#7 0x47e4 in main (argc=1, argv=0xefbfd99c)
at /usr/src/usr.sbin/ypserv/yp_main.c:335
*** By the way, this is applicable to 3.x-Stable as well
If you follow the stack frames up, it is clear that the problem is stemming
from svc_getreqset in libc/rpc/svc.c (which I've included below). I get the
SEGV at the call to SVC_STAT(xprt). Based upon the values of sock and bit:
$31 = (SVCXPRT *) 0x20524fcc
(gdb) p sock
$32 = 0
(gdb) p bit
$33 = 21
(gdb) p *xprt
Error accessing memory address 0x20524fcc: Bad address.
xprt should be pointing to xports[20]. Here is xports[20]
(gdb) p xports[20]
$28 = (SVCXPRT *) 0x0
I think that one of the children processes (or the parent process) may be
calling svctcp_destroy(xprt) or svcudp_destroy(xprt) on the slot that the
parent process (or child process) is working with.
barry
void
svc_getreqset(readfds)
fd_set *readfds;
{
enum xprt_stat stat;
struct rpc_msg msg;
int prog_found;
u_long low_vers;
u_long high_vers;
struct svc_req r;
register SVCXPRT *xprt;
register u_long mask;
register int bit;
register u_long *maskp;
register int setsize;
register int sock;
char cred_area[2*MAX_AUTH_BYTES + RQCRED_SIZE];
msg.rm_call.cb_cred.oa_base = cred_area;
msg.rm_call.cb_verf.oa_base = &(cred_area[MAX_AUTH_BYTES]);
r.rq_clntcred = &(cred_area[2*MAX_AUTH_BYTES]);
setsize = _rpc_dtablesize();
maskp = (u_long *)readfds->fds_bits;
for (sock = 0; sock < setsize; sock += NFDBITS) {
for (mask = *maskp++; (bit = ffs(mask)); mask ^= (1 << (bit - 1))) {
/* sock has input waiting */
xprt = xports[sock + bit - 1];
if (xprt == NULL)
/* But do we control sock? */
continue;
/* now receive msgs from xprtprt (support batch calls) */
do {
if (SVC_RECV(xprt, &msg)) {
/* now find the exported program and call it */
register struct svc_callout *s;
enum auth_stat why;
r.rq_xprt = xprt;
r.rq_prog = msg.rm_call.cb_prog;
r.rq_vers = msg.rm_call.cb_vers;
r.rq_proc = msg.rm_call.cb_proc;
r.rq_cred = msg.rm_call.cb_cred;
/* first authenticate the message */
if ((why= _authenticate(&r, &msg)) != AUTH_OK) {
svcerr_auth(xprt, why);
goto call_done;
}
/* now match message with a registered service*/
prog_found = FALSE;
low_vers = 0 - 1;
high_vers = 0;
for (s = svc_head; s != NULL_SVC; s = s->sc_next) {
if (s->sc_prog == r.rq_prog) {
if (s->sc_vers == r.rq_vers) {
(*s->sc_dispatch)(&r, xprt);
goto call_done;
} /* found correct version */
prog_found = TRUE;
if (s->sc_vers < low_vers)
low_vers = s->sc_vers;
if (s->sc_vers > high_vers)
high_vers = s->sc_vers;
} /* found correct program */
}
/*
* if we got here, the program or version
* is not served ...
*/
if (prog_found)
svcerr_progvers(xprt,
low_vers, high_vers);
else
svcerr_noprog(xprt);
/* Fall through to ... */
}
call_done:
if ((stat = SVC_STAT(xprt)) == XPRT_DIED){
SVC_DESTROY(xprt);
break;
}
} while (stat == XPRT_MOREREQS);
}
}
}
static void
svctcp_destroy(xprt)
register SVCXPRT *xprt;
{
register struct tcp_conn *cd = (struct tcp_conn *)xprt->xp_p1;
xprt_unregister(xprt);
(void)close(xprt->xp_sock);
if (xprt->xp_port != 0) {
/* a rendezvouser socket */
xprt->xp_port = 0;
} else {
/* an actual connection socket */
XDR_DESTROY(&(cd->xdrs));
}
mem_free((caddr_t)cd, sizeof(struct tcp_conn));
mem_free((caddr_t)xprt, sizeof(SVCXPRT));
}
static void
svcudp_destroy(xprt)
register SVCXPRT *xprt;
{
register struct svcudp_data *su = su_data(xprt);
xprt_unregister(xprt);
(void)close(xprt->xp_sock);
XDR_DESTROY(&(su->su_xdrs));
mem_free(rpc_buffer(xprt), su->su_iosz);
mem_free((caddr_t)su, sizeof(struct svcudp_data));
mem_free((caddr_t)xprt, sizeof(SVCXPRT));
}
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message
help
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19990413144409.16671.qmail>