mirror of
https://git.FreeBSD.org/src.git
synced 2024-12-25 11:37:56 +00:00
a34b704666
- sowakeup() now asserts the socket buffer lock on entry. Move the call to KNOTE higher in sowakeup() so that it is made with the socket buffer lock held for consistency with other calls. Release the socket buffer lock prior to calling into pgsigio(), so_upcall(), or aio_swake(). Locking for this event management will need revisiting in the future, but this model avoids lock order reversals when upcalls into other subsystems result in socket/socket buffer operations. Assert that the socket buffer lock is not held at the end of the function. - Wrapper macros for sowakeup(), sorwakeup() and sowwakeup(), now have _locked versions which assert the socket buffer lock on entry. If a wakeup is required by sb_notify(), invoke sowakeup(); otherwise, unconditionally release the socket buffer lock. This results in the socket buffer lock being released whether a wakeup is required or not. - Break out socantsendmore() into socantsendmore_locked() that asserts the socket buffer lock. socantsendmore() unconditionally locks the socket buffer before calling socantsendmore_locked(). Note that both functions return with the socket buffer unlocked as socantsendmore_locked() calls sowwakeup_locked() which has the same properties. Assert that the socket buffer is unlocked on return. - Break out socantrcvmore() into socantrcvmore_locked() that asserts the socket buffer lock. socantrcvmore() unconditionally locks the socket buffer before calling socantrcvmore_locked(). Note that both functions return with the socket buffer unlocked as socantrcvmore_locked() calls sorwakeup_locked() which has similar properties. Assert that the socket buffer is unlocked on return. - Break out sbrelease() into a sbrelease_locked() that asserts the socket buffer lock. sbrelease() unconditionally locks the socket buffer before calling sbrelease_locked(). sbrelease_locked() now invokes sbflush_locked() instead of sbflush(). - Assert the socket buffer lock in socket buffer sanity check functions sblastrecordchk(), sblastmbufchk(). - Assert the socket buffer lock in SBLINKRECORD(). - Break out various sbappend() functions into sbappend_locked() (and variations on that name) that assert the socket buffer lock. The !_locked() variations unconditionally lock the socket buffer before calling their _locked counterparts. Internally, make sure to call _locked() support routines, etc, if already holding the socket buffer lock. - Break out sbinsertoob() into sbinsertoob_locked() that asserts the socket buffer lock. sbinsertoob() unconditionally locks the socket buffer before calling sbinsertoob_locked(). - Break out sbflush() into sbflush_locked() that asserts the socket buffer lock. sbflush() unconditionally locks the socket buffer before calling sbflush_locked(). Update panic strings for new function names. - Break out sbdrop() into sbdrop_locked() that asserts the socket buffer lock. sbdrop() unconditionally locks the socket buffer before calling sbdrop_locked(). - Break out sbdroprecord() into sbdroprecord_locked() that asserts the socket buffer lock. sbdroprecord() unconditionally locks the socket buffer before calling sbdroprecord_locked(). - sofree() now calls socantsendmore_locked() and re-acquires the socket buffer lock on return. It also now calls sbrelease_locked(). - sorflush() now calls socantrcvmore_locked() and re-acquires the socket buffer lock on return. Clean up/mess up other behavior in sorflush() relating to the temporary stack copy of the socket buffer used with dom_dispose by more properly initializing the temporary copy, and selectively bzeroing/copying more carefully to prevent WITNESS from getting confused by improperly initialized mutexes. Annotate why that's necessary, or at least, needed. - soisconnected() now calls sbdrop_locked() before unlocking the socket buffer to avoid locking overhead. Some parts of this change were: Submitted by: sam Sponsored by: FreeBSD Foundation Obtained from: BSD/OS
509 lines
11 KiB
C
509 lines
11 KiB
C
/* $KAME: keysock.c,v 1.32 2003/08/22 05:45:08 itojun Exp $ */
|
|
|
|
/*
|
|
* Copyright (C) 1995, 1996, 1997, and 1998 WIDE Project.
|
|
* 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.
|
|
* 3. Neither the name of the project 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 PROJECT 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 PROJECT 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.
|
|
*/
|
|
|
|
#include <sys/cdefs.h>
|
|
__FBSDID("$FreeBSD$");
|
|
|
|
#include "opt_ipsec.h"
|
|
|
|
/* This code has derived from sys/net/rtsock.c on FreeBSD2.2.5 */
|
|
|
|
#include <sys/types.h>
|
|
#include <sys/param.h>
|
|
#include <sys/domain.h>
|
|
#include <sys/errno.h>
|
|
#include <sys/kernel.h>
|
|
#include <sys/lock.h>
|
|
#include <sys/malloc.h>
|
|
#include <sys/mbuf.h>
|
|
#include <sys/mutex.h>
|
|
#include <sys/protosw.h>
|
|
#include <sys/signalvar.h>
|
|
#include <sys/socket.h>
|
|
#include <sys/socketvar.h>
|
|
#include <sys/sysctl.h>
|
|
#include <sys/systm.h>
|
|
|
|
#include <net/raw_cb.h>
|
|
#include <net/route.h>
|
|
#include <netinet/in.h>
|
|
|
|
#include <net/pfkeyv2.h>
|
|
#include <netkey/keydb.h>
|
|
#include <netkey/key.h>
|
|
#include <netkey/keysock.h>
|
|
#include <netkey/key_debug.h>
|
|
|
|
#include <machine/stdarg.h>
|
|
|
|
struct sockaddr key_dst = { 2, PF_KEY, };
|
|
struct sockaddr key_src = { 2, PF_KEY, };
|
|
|
|
static int key_sendup0(struct rawcb *, struct mbuf *, int);
|
|
|
|
struct pfkeystat pfkeystat;
|
|
|
|
/*
|
|
* key_output()
|
|
*/
|
|
int
|
|
#if __STDC__
|
|
key_output(struct mbuf *m, ...)
|
|
#else
|
|
key_output(m, va_alist)
|
|
struct mbuf *m;
|
|
va_dcl
|
|
#endif
|
|
{
|
|
struct sadb_msg *msg;
|
|
int len, error = 0;
|
|
int s;
|
|
struct socket *so;
|
|
va_list ap;
|
|
|
|
va_start(ap, m);
|
|
so = va_arg(ap, struct socket *);
|
|
va_end(ap);
|
|
|
|
if (m == 0)
|
|
panic("key_output: NULL pointer was passed.");
|
|
|
|
pfkeystat.out_total++;
|
|
pfkeystat.out_bytes += m->m_pkthdr.len;
|
|
|
|
len = m->m_pkthdr.len;
|
|
if (len < sizeof(struct sadb_msg)) {
|
|
pfkeystat.out_tooshort++;
|
|
error = EINVAL;
|
|
goto end;
|
|
}
|
|
|
|
if (m->m_len < sizeof(struct sadb_msg)) {
|
|
if ((m = m_pullup(m, sizeof(struct sadb_msg))) == 0) {
|
|
pfkeystat.out_nomem++;
|
|
error = ENOBUFS;
|
|
goto end;
|
|
}
|
|
}
|
|
|
|
M_ASSERTPKTHDR(m);
|
|
|
|
KEYDEBUG(KEYDEBUG_KEY_DUMP, kdebug_mbuf(m));
|
|
|
|
msg = mtod(m, struct sadb_msg *);
|
|
pfkeystat.out_msgtype[msg->sadb_msg_type]++;
|
|
if (len != PFKEY_UNUNIT64(msg->sadb_msg_len)) {
|
|
pfkeystat.out_invlen++;
|
|
error = EINVAL;
|
|
goto end;
|
|
}
|
|
|
|
/*XXX giant lock*/
|
|
s = splnet();
|
|
error = key_parse(m, so);
|
|
m = NULL;
|
|
splx(s);
|
|
end:
|
|
if (m)
|
|
m_freem(m);
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* send message to the socket.
|
|
*/
|
|
static int
|
|
key_sendup0(rp, m, promisc)
|
|
struct rawcb *rp;
|
|
struct mbuf *m;
|
|
int promisc;
|
|
{
|
|
int error;
|
|
|
|
if (promisc) {
|
|
struct sadb_msg *pmsg;
|
|
|
|
M_PREPEND(m, sizeof(struct sadb_msg), M_DONTWAIT);
|
|
if (m && m->m_len < sizeof(struct sadb_msg))
|
|
m = m_pullup(m, sizeof(struct sadb_msg));
|
|
if (!m) {
|
|
pfkeystat.in_nomem++;
|
|
return ENOBUFS;
|
|
}
|
|
m->m_pkthdr.len += sizeof(*pmsg);
|
|
|
|
pmsg = mtod(m, struct sadb_msg *);
|
|
bzero(pmsg, sizeof(*pmsg));
|
|
pmsg->sadb_msg_version = PF_KEY_V2;
|
|
pmsg->sadb_msg_type = SADB_X_PROMISC;
|
|
pmsg->sadb_msg_len = PFKEY_UNIT64(m->m_pkthdr.len);
|
|
/* pid and seq? */
|
|
|
|
pfkeystat.in_msgtype[pmsg->sadb_msg_type]++;
|
|
}
|
|
|
|
if (!sbappendaddr(&rp->rcb_socket->so_rcv, (struct sockaddr *)&key_src,
|
|
m, NULL)) {
|
|
pfkeystat.in_nomem++;
|
|
m_freem(m);
|
|
error = ENOBUFS;
|
|
} else
|
|
error = 0;
|
|
sorwakeup(rp->rcb_socket);
|
|
return error;
|
|
}
|
|
|
|
/* so can be NULL if target != KEY_SENDUP_ONE */
|
|
int
|
|
key_sendup_mbuf(so, m, target)
|
|
struct socket *so;
|
|
struct mbuf *m;
|
|
int target;
|
|
{
|
|
struct mbuf *n;
|
|
struct keycb *kp;
|
|
int sendup;
|
|
struct rawcb *rp;
|
|
int error = 0;
|
|
|
|
if (m == NULL)
|
|
panic("key_sendup_mbuf: NULL pointer was passed.");
|
|
if (so == NULL && target == KEY_SENDUP_ONE)
|
|
panic("key_sendup_mbuf: NULL pointer was passed.");
|
|
|
|
pfkeystat.in_total++;
|
|
pfkeystat.in_bytes += m->m_pkthdr.len;
|
|
if (m->m_len < sizeof(struct sadb_msg)) {
|
|
m = m_pullup(m, sizeof(struct sadb_msg));
|
|
if (m == NULL) {
|
|
pfkeystat.in_nomem++;
|
|
return ENOBUFS;
|
|
}
|
|
}
|
|
if (m->m_len >= sizeof(struct sadb_msg)) {
|
|
struct sadb_msg *msg;
|
|
msg = mtod(m, struct sadb_msg *);
|
|
pfkeystat.in_msgtype[msg->sadb_msg_type]++;
|
|
}
|
|
|
|
LIST_FOREACH(rp, &rawcb_list, list) {
|
|
if (rp->rcb_proto.sp_family != PF_KEY)
|
|
continue;
|
|
if (rp->rcb_proto.sp_protocol &&
|
|
rp->rcb_proto.sp_protocol != PF_KEY_V2) {
|
|
continue;
|
|
}
|
|
|
|
kp = (struct keycb *)rp;
|
|
|
|
/*
|
|
* If you are in promiscuous mode, and when you get broadcasted
|
|
* reply, you'll get two PF_KEY messages.
|
|
* (based on pf_key@inner.net message on 14 Oct 1998)
|
|
*/
|
|
if (((struct keycb *)rp)->kp_promisc) {
|
|
if ((n = m_copy(m, 0, (int)M_COPYALL)) != NULL) {
|
|
(void)key_sendup0(rp, n, 1);
|
|
n = NULL;
|
|
}
|
|
}
|
|
|
|
/* the exact target will be processed later */
|
|
if (so && sotorawcb(so) == rp)
|
|
continue;
|
|
|
|
sendup = 0;
|
|
switch (target) {
|
|
case KEY_SENDUP_ONE:
|
|
/* the statement has no effect */
|
|
if (so && sotorawcb(so) == rp)
|
|
sendup++;
|
|
break;
|
|
case KEY_SENDUP_ALL:
|
|
sendup++;
|
|
break;
|
|
case KEY_SENDUP_REGISTERED:
|
|
if (kp->kp_registered)
|
|
sendup++;
|
|
break;
|
|
}
|
|
pfkeystat.in_msgtarget[target]++;
|
|
|
|
if (!sendup)
|
|
continue;
|
|
|
|
if ((n = m_copy(m, 0, (int)M_COPYALL)) == NULL) {
|
|
m_freem(m);
|
|
pfkeystat.in_nomem++;
|
|
return ENOBUFS;
|
|
}
|
|
|
|
/*
|
|
* ignore error even if queue is full. PF_KEY does not
|
|
* guarantee the delivery of the message.
|
|
* this is important when target == KEY_SENDUP_ALL.
|
|
*/
|
|
key_sendup0(rp, n, 0);
|
|
|
|
n = NULL;
|
|
}
|
|
|
|
if (so) {
|
|
error = key_sendup0(sotorawcb(so), m, 0);
|
|
m = NULL;
|
|
} else {
|
|
error = 0;
|
|
m_freem(m);
|
|
}
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* key_abort()
|
|
* derived from net/rtsock.c:rts_abort()
|
|
*/
|
|
static int
|
|
key_abort(struct socket *so)
|
|
{
|
|
int s, error;
|
|
s = splnet();
|
|
error = raw_usrreqs.pru_abort(so);
|
|
splx(s);
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* key_attach()
|
|
* derived from net/rtsock.c:rts_attach()
|
|
*/
|
|
static int
|
|
key_attach(struct socket *so, int proto, struct thread *td)
|
|
{
|
|
struct keycb *kp;
|
|
int s, error;
|
|
|
|
if (sotorawcb(so) != 0)
|
|
return EISCONN; /* XXX panic? */
|
|
kp = (struct keycb *)malloc(sizeof *kp, M_PCB, M_WAITOK); /* XXX */
|
|
if (kp == 0)
|
|
return ENOBUFS;
|
|
bzero(kp, sizeof *kp);
|
|
|
|
/*
|
|
* The splnet() is necessary to block protocols from sending
|
|
* error notifications (like RTM_REDIRECT or RTM_LOSING) while
|
|
* this PCB is extant but incompletely initialized.
|
|
* Probably we should try to do more of this work beforehand and
|
|
* eliminate the spl.
|
|
*/
|
|
s = splnet();
|
|
so->so_pcb = (caddr_t)kp;
|
|
error = raw_usrreqs.pru_attach(so, proto, td);
|
|
kp = (struct keycb *)sotorawcb(so);
|
|
if (error) {
|
|
free(kp, M_PCB);
|
|
so->so_pcb = (caddr_t) 0;
|
|
splx(s);
|
|
return error;
|
|
}
|
|
|
|
kp->kp_promisc = kp->kp_registered = 0;
|
|
|
|
if (kp->kp_raw.rcb_proto.sp_protocol == PF_KEY) /* XXX: AF_KEY */
|
|
key_cb.key_count++;
|
|
key_cb.any_count++;
|
|
kp->kp_raw.rcb_laddr = &key_src;
|
|
kp->kp_raw.rcb_faddr = &key_dst;
|
|
soisconnected(so);
|
|
so->so_options |= SO_USELOOPBACK;
|
|
|
|
splx(s);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* key_bind()
|
|
* derived from net/rtsock.c:rts_bind()
|
|
*/
|
|
static int
|
|
key_bind(struct socket *so, struct sockaddr *nam, struct thread *td)
|
|
{
|
|
int s, error;
|
|
s = splnet();
|
|
error = raw_usrreqs.pru_bind(so, nam, td); /* xxx just EINVAL */
|
|
splx(s);
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* key_connect()
|
|
* derived from net/rtsock.c:rts_connect()
|
|
*/
|
|
static int
|
|
key_connect(struct socket *so, struct sockaddr *nam, struct thread *td)
|
|
{
|
|
int s, error;
|
|
s = splnet();
|
|
error = raw_usrreqs.pru_connect(so, nam, td); /* XXX just EINVAL */
|
|
splx(s);
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* key_detach()
|
|
* derived from net/rtsock.c:rts_detach()
|
|
*/
|
|
static int
|
|
key_detach(struct socket *so)
|
|
{
|
|
struct keycb *kp = (struct keycb *)sotorawcb(so);
|
|
int s, error;
|
|
|
|
s = splnet();
|
|
if (kp != 0) {
|
|
if (kp->kp_raw.rcb_proto.sp_protocol
|
|
== PF_KEY) /* XXX: AF_KEY */
|
|
key_cb.key_count--;
|
|
key_cb.any_count--;
|
|
|
|
key_freereg(so);
|
|
}
|
|
error = raw_usrreqs.pru_detach(so);
|
|
splx(s);
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* key_disconnect()
|
|
* derived from net/rtsock.c:key_disconnect()
|
|
*/
|
|
static int
|
|
key_disconnect(struct socket *so)
|
|
{
|
|
int s, error;
|
|
s = splnet();
|
|
error = raw_usrreqs.pru_disconnect(so);
|
|
splx(s);
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* key_peeraddr()
|
|
* derived from net/rtsock.c:rts_peeraddr()
|
|
*/
|
|
static int
|
|
key_peeraddr(struct socket *so, struct sockaddr **nam)
|
|
{
|
|
int s, error;
|
|
s = splnet();
|
|
error = raw_usrreqs.pru_peeraddr(so, nam);
|
|
splx(s);
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* key_send()
|
|
* derived from net/rtsock.c:rts_send()
|
|
*/
|
|
static int
|
|
key_send(struct socket *so, int flags, struct mbuf *m, struct sockaddr *nam,
|
|
struct mbuf *control, struct thread *td)
|
|
{
|
|
int s, error;
|
|
s = splnet();
|
|
error = raw_usrreqs.pru_send(so, flags, m, nam, control, td);
|
|
splx(s);
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* key_shutdown()
|
|
* derived from net/rtsock.c:rts_shutdown()
|
|
*/
|
|
static int
|
|
key_shutdown(struct socket *so)
|
|
{
|
|
int s, error;
|
|
s = splnet();
|
|
error = raw_usrreqs.pru_shutdown(so);
|
|
splx(s);
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* key_sockaddr()
|
|
* derived from net/rtsock.c:rts_sockaddr()
|
|
*/
|
|
static int
|
|
key_sockaddr(struct socket *so, struct sockaddr **nam)
|
|
{
|
|
int s, error;
|
|
s = splnet();
|
|
error = raw_usrreqs.pru_sockaddr(so, nam);
|
|
splx(s);
|
|
return error;
|
|
}
|
|
|
|
struct pr_usrreqs key_usrreqs = {
|
|
key_abort, pru_accept_notsupp, key_attach, key_bind,
|
|
key_connect,
|
|
pru_connect2_notsupp, pru_control_notsupp, key_detach,
|
|
key_disconnect, pru_listen_notsupp, key_peeraddr,
|
|
pru_rcvd_notsupp,
|
|
pru_rcvoob_notsupp, key_send, pru_sense_null, key_shutdown,
|
|
key_sockaddr, sosend, soreceive, sopoll,
|
|
pru_sosetlabel_null
|
|
};
|
|
|
|
/* sysctl */
|
|
SYSCTL_NODE(_net, PF_KEY, key, CTLFLAG_RW, 0, "Key Family");
|
|
|
|
/*
|
|
* Definitions of protocols supported in the KEY domain.
|
|
*/
|
|
|
|
extern struct domain keydomain;
|
|
|
|
struct protosw keysw[] = {
|
|
{ SOCK_RAW, &keydomain, PF_KEY_V2, PR_ATOMIC|PR_ADDR,
|
|
0, (pr_output_t *)key_output, raw_ctlinput, 0,
|
|
0,
|
|
raw_init, 0, 0, 0,
|
|
&key_usrreqs
|
|
}
|
|
};
|
|
|
|
struct domain keydomain =
|
|
{ PF_KEY, "key", key_init, 0, 0,
|
|
keysw, &keysw[sizeof(keysw)/sizeof(keysw[0])] };
|
|
|
|
DOMAIN_SET(key);
|