freebsd-dev/sys/netinet/tcp_reass.c

364 lines
10 KiB
C
Raw Normal View History

/*-
* Copyright (c) 1982, 1986, 1988, 1990, 1993, 1994, 1995
1994-05-24 10:09:53 +00:00
* The Regents of the University of California. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)tcp_input.c 8.12 (Berkeley) 5/24/95
1994-05-24 10:09:53 +00:00
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
Initial import of RFC 2385 (TCP-MD5) digest support. This is the first of two commits; bringing in the kernel support first. This can be enabled by compiling a kernel with options TCP_SIGNATURE and FAST_IPSEC. For the uninitiated, this is a TCP option which provides for a means of authenticating TCP sessions which came into being before IPSEC. It is still relevant today, however, as it is used by many commercial router vendors, particularly with BGP, and as such has become a requirement for interconnect at many major Internet points of presence. Several parts of the TCP and IP headers, including the segment payload, are digested with MD5, including a shared secret. The PF_KEY interface is used to manage the secrets using security associations in the SADB. There is a limitation here in that as there is no way to map a TCP flow per-port back to an SPI without polluting tcpcb or using the SPD; the code to do the latter is unstable at this time. Therefore this code only supports per-host keying granularity. Whilst FAST_IPSEC is mutually exclusive with KAME IPSEC (and thus IPv6), TCP_SIGNATURE applies only to IPv4. For the vast majority of prospective users of this feature, this will not pose any problem. This implementation is output-only; that is, the option is honoured when responding to a host initiating a TCP session, but no effort is made [yet] to authenticate inbound traffic. This is, however, sufficient to interwork with Cisco equipment. Tested with a Cisco 2501 running IOS 12.0(27), and Quagga 0.96.4 with local patches. Patches for tcpdump to validate TCP-MD5 sessions are also available from me upon request. Sponsored by: sentex.net
2004-02-11 04:26:04 +00:00
#include "opt_inet.h"
#include "opt_inet6.h"
1997-09-16 18:36:06 +00:00
#include "opt_tcpdebug.h"
1994-05-24 10:09:53 +00:00
#include <sys/param.h>
#include <sys/kernel.h>
1994-05-24 10:09:53 +00:00
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>
#include <sys/systm.h>
1994-05-24 10:09:53 +00:00
#include <vm/uma.h>
1994-05-24 10:09:53 +00:00
#include <net/if.h>
#include <net/route.h>
#include <net/vnet.h>
1994-05-24 10:09:53 +00:00
#include <netinet/in.h>
#include <netinet/in_pcb.h>
1994-05-24 10:09:53 +00:00
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
1994-05-24 10:09:53 +00:00
#include <netinet/ip.h>
#include <netinet/ip_var.h>
#include <netinet/ip_options.h>
#include <netinet/ip6.h>
#include <netinet6/in6_pcb.h>
#include <netinet6/ip6_var.h>
#include <netinet6/nd6.h>
1994-05-24 10:09:53 +00:00
#include <netinet/tcp.h>
#include <netinet/tcp_fsm.h>
#include <netinet/tcp_seq.h>
#include <netinet/tcp_timer.h>
#include <netinet/tcp_var.h>
#include <netinet6/tcp6_var.h>
1994-05-24 10:09:53 +00:00
#include <netinet/tcpip.h>
#ifdef TCPDEBUG
1994-05-24 10:09:53 +00:00
#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);
static SYSCTL_NODE(_net_inet_tcp, OID_AUTO, reass, CTLFLAG_RW, 0,
2007-03-19 19:00:51 +00:00
"TCP Segment Reassembly Queue");
static VNET_DEFINE(int, tcp_reass_maxseg) = 0;
#define V_tcp_reass_maxseg VNET(tcp_reass_maxseg)
SYSCTL_VNET_PROC(_net_inet_tcp_reass, OID_AUTO, maxsegments,
CTLTYPE_INT | CTLFLAG_RDTUN,
&VNET_NAME(tcp_reass_maxseg), 0, &tcp_reass_sysctl_maxseg, "I",
2007-03-19 19:00:51 +00:00
"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_PROC(_net_inet_tcp_reass, OID_AUTO, cursegments,
CTLTYPE_INT | CTLFLAG_RD,
&VNET_NAME(tcp_reass_qsize), 0, &tcp_reass_sysctl_qsize, "I",
2007-03-19 19:00:51 +00:00
"Global number of TCP Segments currently in Reassembly Queue");
static VNET_DEFINE(int, tcp_reass_overflows) = 0;
#define V_tcp_reass_overflows VNET(tcp_reass_overflows)
SYSCTL_VNET_INT(_net_inet_tcp_reass, OID_AUTO, overflows,
CTLTYPE_INT | CTLFLAG_RD,
Build on Jeff Roberson's linker-set based dynamic per-CPU allocator (DPCPU), as suggested by Peter Wemm, and implement a new per-virtual network stack memory allocator. Modify vnet to use the allocator instead of monolithic global container structures (vinet, ...). This change solves many binary compatibility problems associated with VIMAGE, and restores ELF symbols for virtualized global variables. Each virtualized global variable exists as a "reference copy", and also once per virtual network stack. Virtualized global variables are tagged at compile-time, placing the in a special linker set, which is loaded into a contiguous region of kernel memory. Virtualized global variables in the base kernel are linked as normal, but those in modules are copied and relocated to a reserved portion of the kernel's vnet region with the help of a the kernel linker. Virtualized global variables exist in per-vnet memory set up when the network stack instance is created, and are initialized statically from the reference copy. Run-time access occurs via an accessor macro, which converts from the current vnet and requested symbol to a per-vnet address. When "options VIMAGE" is not compiled into the kernel, normal global ELF symbols will be used instead and indirection is avoided. This change restores static initialization for network stack global variables, restores support for non-global symbols and types, eliminates the need for many subsystem constructors, eliminates large per-subsystem structures that caused many binary compatibility issues both for monitoring applications (netstat) and kernel modules, removes the per-function INIT_VNET_*() macros throughout the stack, eliminates the need for vnet_symmap ksym(2) munging, and eliminates duplicate definitions of virtualized globals under VIMAGE_GLOBALS. Bump __FreeBSD_version and update UPDATING. Portions submitted by: bz Reviewed by: bz, zec Discussed with: gnn, jamie, jeff, jhb, julian, sam Suggested by: peter Approved by: re (kensmith)
2009-07-14 22:48:30 +00:00
&VNET_NAME(tcp_reass_overflows), 0,
2007-03-19 19:00:51 +00:00
"Global number of TCP Segment Reassembly Queue Overflows");
static VNET_DEFINE(uma_zone_t, tcp_reass_zone);
#define V_tcp_reass_zone VNET(tcp_reass_zone)
/* Initialize TCP reassembly queue */
static void
tcp_reass_zone_change(void *tag)
{
V_tcp_reass_maxseg = nmbclusters / 16;
uma_zone_set_max(V_tcp_reass_zone, V_tcp_reass_maxseg);
}
void
tcp_reass_init(void)
{
V_tcp_reass_maxseg = nmbclusters / 16;
TUNABLE_INT_FETCH("net.inet.tcp.reass.maxsegments",
&V_tcp_reass_maxseg);
V_tcp_reass_zone = uma_zcreate("tcpreass", sizeof (struct tseg_qent),
NULL, NULL, NULL, NULL, UMA_ALIGN_PTR, UMA_ZONE_NOFREE);
uma_zone_set_max(V_tcp_reass_zone, V_tcp_reass_maxseg);
EVENTHANDLER_REGISTER(nmbclusters_change,
tcp_reass_zone_change, NULL, EVENTHANDLER_PRI_ANY);
}
#ifdef VIMAGE
void
tcp_reass_destroy(void)
{
uma_zdestroy(V_tcp_reass_zone);
}
#endif
void
tcp_reass_flush(struct tcpcb *tp)
{
struct tseg_qent *qe;
INP_WLOCK_ASSERT(tp->t_inpcb);
while ((qe = LIST_FIRST(&tp->t_segq)) != NULL) {
LIST_REMOVE(qe, tqe_q);
m_freem(qe->tqe_m);
uma_zfree(V_tcp_reass_zone, qe);
tp->t_segqlen--;
}
KASSERT((tp->t_segqlen == 0),
("TCP reass queue %p segment count is %d instead of 0 after flush.",
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)
1994-05-24 10:09:53 +00:00
{
struct tseg_qent *q;
struct tseg_qent *p = NULL;
struct tseg_qent *nq;
struct tseg_qent *te = NULL;
1994-05-24 10:09:53 +00:00
struct socket *so = tp->t_inpcb->inp_socket;
char *s = NULL;
1994-05-24 10:09:53 +00:00
int flags;
struct tseg_qent tqs;
1994-05-24 10:09:53 +00:00
INP_WLOCK_ASSERT(tp->t_inpcb);
/*
* XXX: tcp_reass() is rather inefficient with its data structures
* and should be rewritten (see NetBSD for optimizations).
*/
1994-05-24 10:09:53 +00:00
/*
* Call with th==NULL after become established to
1994-05-24 10:09:53 +00:00
* force pre-ESTABLISHED data up to user socket.
*/
if (th == NULL)
1994-05-24 10:09:53 +00:00
goto present;
/*
* Limit the number of segments that can be queued to reduce the
* potential for mbuf exhaustion. For best performance, we want to be
* able to queue a full window's worth of segments. The size of the
* socket receive buffer determines our advertised window and grows
* automatically when socket buffer autotuning is enabled. Use it as the
* basis for our queue limit.
* Always let the missing segment through which caused this queue.
* NB: Access to the socket buffer is left intentionally unlocked as we
* can tolerate stale information here.
*
* XXXLAS: Using sbspace(so->so_rcv) instead of so->so_rcv.sb_hiwat
* should work but causes packets to be dropped when they shouldn't.
* Investigate why and re-evaluate the below limit after the behaviour
* is understood.
*/
if (th->th_seq != tp->rcv_nxt &&
tp->t_segqlen >= (so->so_rcv.sb_hiwat / tp->t_maxseg) + 1) {
V_tcp_reass_overflows++;
TCPSTAT_INC(tcps_rcvmemdrop);
m_freem(m);
*tlenp = 0;
if ((s = tcp_log_addrs(&tp->t_inpcb->inp_inc, th, NULL, NULL))) {
log(LOG_DEBUG, "%s; %s: queue limit reached, "
"segment dropped\n", s, __func__);
free(s, M_TCPLOG);
}
return (0);
}
/*
* Allocate a new queue entry. If we can't, or hit the zone limit
* just drop the pkt.
*
* Use a temporary structure on the stack for the missing segment
* when the zone is exhausted. Otherwise we may get stuck.
*/
te = uma_zalloc(V_tcp_reass_zone, M_NOWAIT);
if (te == NULL && th->th_seq != tp->rcv_nxt) {
TCPSTAT_INC(tcps_rcvmemdrop);
m_freem(m);
*tlenp = 0;
if ((s = tcp_log_addrs(&tp->t_inpcb->inp_inc, th, NULL, NULL))) {
log(LOG_DEBUG, "%s; %s: global zone limit reached, "
"segment dropped\n", s, __func__);
free(s, M_TCPLOG);
}
return (0);
} else if (th->th_seq == tp->rcv_nxt) {
bzero(&tqs, sizeof(struct tseg_qent));
te = &tqs;
if ((s = tcp_log_addrs(&tp->t_inpcb->inp_inc, th, NULL, NULL))) {
log(LOG_DEBUG, "%s; %s: global zone limit reached, "
"using stack for missing segment\n", s, __func__);
free(s, M_TCPLOG);
}
}
tp->t_segqlen++;
1994-05-24 10:09:53 +00:00
/*
* Find a segment which begins after this one does.
*/
LIST_FOREACH(q, &tp->t_segq, tqe_q) {
if (SEQ_GT(q->tqe_th->th_seq, th->th_seq))
1994-05-24 10:09:53 +00:00
break;
p = q;
}
1994-05-24 10:09:53 +00:00
/*
* If there is a preceding segment, it may provide some of
* our data already. If so, drop the data from the incoming
* segment. If it provides all of our data, drop us.
*/
if (p != NULL) {
int i;
1994-05-24 10:09:53 +00:00
/* conversion to int (in i) handles seq wraparound */
i = p->tqe_th->th_seq + p->tqe_len - th->th_seq;
1994-05-24 10:09:53 +00:00
if (i > 0) {
if (i >= *tlenp) {
TCPSTAT_INC(tcps_rcvduppack);
TCPSTAT_ADD(tcps_rcvdupbyte, *tlenp);
1994-05-24 10:09:53 +00:00
m_freem(m);
uma_zfree(V_tcp_reass_zone, te);
tp->t_segqlen--;
/*
* Try to present any queued data
* at the left window edge to the user.
* This is needed after the 3-WHS
* completes.
*/
goto present; /* ??? */
1994-05-24 10:09:53 +00:00
}
m_adj(m, i);
*tlenp -= i;
th->th_seq += i;
1994-05-24 10:09:53 +00:00
}
}
2011-01-07 21:40:34 +00:00
tp->t_rcvoopack++;
TCPSTAT_INC(tcps_rcvoopack);
TCPSTAT_ADD(tcps_rcvoobyte, *tlenp);
1994-05-24 10:09:53 +00:00
/*
* While we overlap succeeding segments trim them or,
* if they are completely covered, dequeue them.
*/
while (q) {
int i = (th->th_seq + *tlenp) - q->tqe_th->th_seq;
1994-05-24 10:09:53 +00:00
if (i <= 0)
break;
if (i < q->tqe_len) {
q->tqe_th->th_seq += i;
q->tqe_len -= i;
m_adj(q->tqe_m, i);
1994-05-24 10:09:53 +00:00
break;
}
nq = LIST_NEXT(q, tqe_q);
LIST_REMOVE(q, tqe_q);
m_freem(q->tqe_m);
uma_zfree(V_tcp_reass_zone, q);
tp->t_segqlen--;
q = nq;
1994-05-24 10:09:53 +00:00
}
/* Insert the new segment queue entry into place. */
te->tqe_m = m;
te->tqe_th = th;
te->tqe_len = *tlenp;
if (p == NULL) {
LIST_INSERT_HEAD(&tp->t_segq, te, tqe_q);
} else {
KASSERT(te != &tqs, ("%s: temporary stack based entry not "
"first element in queue", __func__));
LIST_INSERT_AFTER(p, te, tqe_q);
}
1994-05-24 10:09:53 +00:00
present:
/*
* Present data to user, advancing rcv_nxt through
* completed sequence space.
*/
if (!TCPS_HAVEESTABLISHED(tp->t_state))
1994-05-24 10:09:53 +00:00
return (0);
q = LIST_FIRST(&tp->t_segq);
if (!q || q->tqe_th->th_seq != tp->rcv_nxt)
1994-05-24 10:09:53 +00:00
return (0);
SOCKBUF_LOCK(&so->so_rcv);
1994-05-24 10:09:53 +00:00
do {
tp->rcv_nxt += q->tqe_len;
flags = q->tqe_th->th_flags & TH_FIN;
nq = LIST_NEXT(q, tqe_q);
LIST_REMOVE(q, tqe_q);
if (so->so_rcv.sb_state & SBS_CANTRCVMORE)
m_freem(q->tqe_m);
else
sbappendstream_locked(&so->so_rcv, q->tqe_m);
if (q != &tqs)
uma_zfree(V_tcp_reass_zone, q);
tp->t_segqlen--;
q = nq;
} while (q && q->tqe_th->th_seq == tp->rcv_nxt);
ND6_HINT(tp);
sorwakeup_locked(so);
1994-05-24 10:09:53 +00:00
return (flags);
}