6fb8880601
See the following descriptions for details. Proposed on tech-kern and tech-net Overview -------- We protect the routing table with a rwock and protect rtcaches with another rwlock. Each rtentry is protected from being freed or updated via reference counting and psref. Global rwlocks -------------- There are two rwlocks; one for the routing table (rt_lock) and the other for rtcaches (rtcache_lock). rtcache_lock covers all existing rtcaches; there may have room for optimizations (future work). The locking order is rtcache_lock first and rt_lock is next. rtentry references ------------------ References to an rtentry is managed with reference counting and psref. Either of the two mechanisms is used depending on where a rtentry is obtained. Reference counting is used when we obtain a rtentry from the routing table directly via rtalloc1 and rtrequest{,1} while psref is used when we obtain a rtentry from a rtcache via rtcache_* APIs. In both cases, a caller can sleep/block with holding an obtained rtentry. The reasons why we use two different mechanisms are (i) only using reference counting hurts the performance due to atomic instructions (rtcache case) (ii) ease of implementation; applying psref to APIs such rtaloc1 and rtrequest{,1} requires additional works (adding a local variable and an argument). We will finally migrate to use only psref but we can do it when we have a lockless routing table alternative. Reference counting for rtentry ------------------------------ rt_refcnt now doesn't count permanent references such as for rt_timers and rtcaches, instead it is used only for temporal references when obtaining a rtentry via rtalloc1 and rtrequest{,1}. We can do so because destroying a rtentry always involves removing references of rt_timers and rtcaches to the rtentry and we don't need to track such references. This also makes it easy to wait for readers to release references on deleting or updating a rtentry, i.e., we can simply wait until the reference counter is 0 or 1. (If there are permanent references the counter can be arbitrary.) rt_ref increments a reference counter of a rtentry and rt_unref decrements it. rt_ref is called inside APIs (rtalloc1 and rtrequest{,1} so users don't need to care about it while users must call rt_unref to an obtained rtentry after using it. rtfree is removed and we use rt_unref and rt_free instead. rt_unref now just decrements the counter of a given rtentry and rt_free just tries to destroy a given rtentry. See the next section for destructions of rtentries by rt_free. Destructions of rtentries ------------------------- We destroy a rtentry only when we call rtrequst{,1}(RTM_DELETE); the original implementation can destroy in any rtfree where it's the last reference. If we use reference counting or psref, it's easy to understand if the place that a rtentry is destroyed is fixed. rt_free waits for references to a given rtentry to be released before actually destroying the rtentry. rt_free uses a condition variable (cv_wait) (and psref_target_destroy for psref) to wait. Unfortunately rtrequst{,1}(RTM_DELETE) can be called in softint that we cannot use cv_wait. In that case, we have to defer the destruction to a workqueue. rtentry#rt_cv, rtentry#rt_psref and global variables (see rt_free_global) are added to conduct the procedure. Updates of rtentries -------------------- One difficulty to use refcnt/psref instead of rwlock for rtentry is updates of rtentries. We need an additional mechanism to prevent readers from seeing inconsistency of a rtentry being updated. We introduce RTF_UPDATING flag to rtentries that are updating. While the flag is set to a rtentry, users cannot acquire the rtentry. By doing so, we avoid users to see inconsistent rtentries. There are two options when a user tries to acquire a rtentry with the RTF_UPDATING flag; if a user runs in softint context the user fails to acquire a rtentry (NULL is returned). Otherwise a user waits until the update completes by waiting on cv. The procedure of a updater is simpler to destruction of a rtentry. Wait on cv (and psref) and after all readers left, proceed with the update. Global variables (see rt_update_global) are added to conduct the procedure. Currently we apply the mechanism to only RTM_CHANGE in rtsock.c. We would have to apply other codes. See "Known issues" section. psref for rtentry ----------------- When we obtain a rtentry from a rtcache via rtcache_* APIs, psref is used to reference to the rtentry. rtcache_ref acquires a reference to a rtentry with psref and rtcache_unref releases the reference after using it. rtcache_ref is called inside rtcache_* APIs and users don't need to take care of it while users must call rtcache_unref to release the reference. struct psref and int bound that is needed for psref is embedded into struct route. By doing so we don't need to add local variables and additional argument to APIs. However this adds another constraint to psref other than reference counting one's; holding a reference of an rtentry via a rtcache is allowed by just one caller at the same time. So we must not acquire a rtentry via a rtcache twice and avoid a recursive use of a rtcache. And also a rtcache must be arranged to be used by a LWP/softint at the same time somehow. For IP forwarding case, we have per-CPU rtcaches used in softint so the constraint is guaranteed. For a h rtcache of a PCB case, the constraint is guaranteed by the solock of each PCB. Any other cases (pf, ipf, stf and ipsec) are currently guaranteed by only the existence of the global locks (softnet_lock and/or KERNEL_LOCK). If we've found the cases that we cannot guarantee the constraint, we would need to introduce other rtcache APIs that use simple reference counting. psref of rtcache is created with IPL_SOFTNET and so rtcache shouldn't used at an IPL higher than IPL_SOFTNET. Note that rtcache_free is used to invalidate a given rtcache. We don't need another care by my change; just keep them as they are. Performance impact ------------------ When NET_MPSAFE is disabled the performance drop is 3% while when it's enabled the drop is increased to 11%. The difference comes from that currently we don't take any global locks and don't use psref if NET_MPSAFE is disabled. We can optimize the performance of the case of NET_MPSAFE on by reducing lookups of rtcache that uses psref; currently we do two lookups but we should be able to trim one of two. This is a future work. Known issues ------------ There are two known issues to be solved; one is that a caller of rtrequest(RTM_ADD) may change rtentry (see rtinit). We need to prevent new references during the update. Or we may be able to remove the code (perhaps, need more investigations). The other is rtredirect that updates a rtentry. We need to apply our update mechanism, however it's not easy because rtredirect is called in softint and we cannot apply our mechanism simply. One solution is to defer rtredirect to a workqueue but it requires some code restructuring.
262 lines
6.8 KiB
C
262 lines
6.8 KiB
C
/* $NetBSD: if_atm.c,v 1.39 2016/12/12 03:55:57 ozaki-r Exp $ */
|
|
|
|
/*
|
|
* Copyright (c) 1996 Charles D. Cranor and Washington University.
|
|
* 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.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``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 AUTHOR 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.
|
|
*/
|
|
|
|
/*
|
|
* IP <=> ATM address resolution.
|
|
*/
|
|
|
|
#include <sys/cdefs.h>
|
|
__KERNEL_RCSID(0, "$NetBSD: if_atm.c,v 1.39 2016/12/12 03:55:57 ozaki-r Exp $");
|
|
|
|
#ifdef _KERNEL_OPT
|
|
#include "opt_inet.h"
|
|
#include "opt_natm.h"
|
|
#endif
|
|
|
|
#if defined(INET) || defined(INET6)
|
|
|
|
#include <sys/param.h>
|
|
#include <sys/systm.h>
|
|
#include <sys/mbuf.h>
|
|
#include <sys/socket.h>
|
|
#include <sys/time.h>
|
|
#include <sys/kernel.h>
|
|
#include <sys/errno.h>
|
|
#include <sys/ioctl.h>
|
|
#include <sys/syslog.h>
|
|
#include <sys/proc.h>
|
|
|
|
#include <net/if.h>
|
|
#include <net/if_dl.h>
|
|
#include <net/route.h>
|
|
#include <net/if_atm.h>
|
|
|
|
#include <netinet/in.h>
|
|
#include <netinet/in_systm.h>
|
|
#include <netinet/in_var.h>
|
|
#include <netinet/ip.h>
|
|
#include <netinet/if_atm.h>
|
|
|
|
#ifdef NATM
|
|
#include <netnatm/natm.h>
|
|
#endif
|
|
|
|
|
|
/*
|
|
* atm_rtrequest: handle ATM rt request (in support of generic code)
|
|
* inputs: "req" = request code
|
|
* "rt" = route entry
|
|
* "sa" = sockaddr
|
|
*/
|
|
|
|
void
|
|
atm_rtrequest(int req, struct rtentry *rt, const struct rt_addrinfo *info)
|
|
{
|
|
struct sockaddr *gate = rt->rt_gateway;
|
|
struct atm_pseudoioctl api;
|
|
#ifdef NATM
|
|
const struct sockaddr_in *sin;
|
|
struct natmpcb *npcb = NULL;
|
|
const struct atm_pseudohdr *aph;
|
|
#endif
|
|
const struct ifnet *ifp = rt->rt_ifp;
|
|
uint8_t namelen = strlen(ifp->if_xname);
|
|
uint8_t addrlen = ifp->if_addrlen;
|
|
|
|
if (rt->rt_flags & RTF_GATEWAY) /* link level requests only */
|
|
return;
|
|
|
|
switch (req) {
|
|
|
|
case RTM_ADD:
|
|
|
|
/*
|
|
* route added by a command (e.g. ifconfig, route, arp...).
|
|
*
|
|
* first check to see if this is not a host route, in which
|
|
* case we are being called via "ifconfig" to set the address.
|
|
*/
|
|
|
|
if ((rt->rt_flags & RTF_HOST) == 0) {
|
|
union {
|
|
struct sockaddr sa;
|
|
struct sockaddr_dl sdl;
|
|
struct sockaddr_storage ss;
|
|
} u;
|
|
|
|
sockaddr_dl_init(&u.sdl, sizeof(u.ss),
|
|
ifp->if_index, ifp->if_type,
|
|
NULL, namelen, NULL, addrlen);
|
|
rt_setgate(rt, &u.sa);
|
|
gate = rt->rt_gateway;
|
|
break;
|
|
}
|
|
|
|
if (gate->sa_family != AF_LINK ||
|
|
gate->sa_len < sockaddr_dl_measure(namelen, addrlen)) {
|
|
log(LOG_DEBUG, "atm_rtrequest: bad gateway value\n");
|
|
break;
|
|
}
|
|
|
|
#ifdef DIAGNOSTIC
|
|
if (rt->rt_ifp->if_ioctl == NULL) panic("atm null ioctl");
|
|
#endif
|
|
|
|
#ifdef NATM
|
|
/*
|
|
* let native ATM know we are using this VCI/VPI
|
|
* (i.e. reserve it)
|
|
*/
|
|
sin = satocsin(rt_getkey(rt));
|
|
if (sin->sin_family != AF_INET)
|
|
goto failed;
|
|
aph = (const struct atm_pseudohdr *)CLLADDR(satosdl(gate));
|
|
npcb = npcb_add(NULL, rt->rt_ifp, ATM_PH_VCI(aph),
|
|
ATM_PH_VPI(aph));
|
|
if (npcb == NULL)
|
|
goto failed;
|
|
npcb->npcb_flags |= NPCB_IP;
|
|
npcb->ipaddr.s_addr = sin->sin_addr.s_addr;
|
|
/* XXX: move npcb to llinfo when ATM ARP is ready */
|
|
rt->rt_llinfo = (void *) npcb;
|
|
#endif
|
|
/*
|
|
* let the lower level know this circuit is active
|
|
*/
|
|
memcpy(&api.aph, CLLADDR(satocsdl(gate)), sizeof(api.aph));
|
|
api.rxhand = NULL;
|
|
if (rt->rt_ifp->if_ioctl(rt->rt_ifp, SIOCATMENA, &api) != 0) {
|
|
printf("atm: couldn't add VC\n");
|
|
goto failed;
|
|
}
|
|
|
|
satosdl(gate)->sdl_type = rt->rt_ifp->if_type;
|
|
satosdl(gate)->sdl_index = rt->rt_ifp->if_index;
|
|
|
|
break;
|
|
|
|
failed:
|
|
#ifdef NATM
|
|
if (npcb) {
|
|
npcb_free(npcb, NPCB_DESTROY);
|
|
rt->rt_llinfo = NULL;
|
|
}
|
|
#endif
|
|
rtrequest(RTM_DELETE, rt_getkey(rt), NULL,
|
|
rt_mask(rt), 0, NULL);
|
|
break;
|
|
|
|
case RTM_DELETE:
|
|
|
|
/*
|
|
* tell the lower layer to disable this circuit
|
|
*/
|
|
|
|
memcpy(&api.aph, CLLADDR(satocsdl(gate)), sizeof(api.aph));
|
|
api.rxhand = NULL;
|
|
(void)rt->rt_ifp->if_ioctl(rt->rt_ifp, SIOCATMDIS, &api);
|
|
|
|
break;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* atmresolve:
|
|
* inputs:
|
|
* [1] "rt" = the link level route to use (or null if need to look one up)
|
|
* [2] "m" = mbuf containing the data to be sent
|
|
* [3] "dst" = sockaddr_in (IP) address of dest.
|
|
* output:
|
|
* [4] "desten" = ATM pseudo header which we will fill in VPI/VCI info
|
|
* return:
|
|
* 0 == resolve FAILED; note that "m" gets m_freem'd in this case
|
|
* 1 == resolve OK; desten contains result
|
|
*
|
|
* XXX: will need more work if we wish to support ATMARP in the kernel,
|
|
* but this is enough for PVCs entered via the "route" command.
|
|
*/
|
|
|
|
int
|
|
atmresolve(const struct rtentry *rt0, struct mbuf *m, const struct sockaddr *dst,
|
|
struct atm_pseudohdr *desten /* OUT */)
|
|
{
|
|
const struct sockaddr_dl *sdl;
|
|
struct rtentry *rt = NULL;
|
|
|
|
if (m->m_flags & (M_BCAST|M_MCAST)) {
|
|
log(LOG_INFO, "atmresolve: BCAST/MCAST packet detected/dumped\n");
|
|
goto bad;
|
|
}
|
|
|
|
if (rt0 == NULL) {
|
|
rt = RTALLOC1(dst, 0);
|
|
if (rt == NULL)
|
|
goto bad; /* failed */
|
|
if ((rt->rt_flags & RTF_GATEWAY) != 0 ||
|
|
/* XXX: are we using LLINFO? */
|
|
rt->rt_gateway->sa_family != AF_LINK) {
|
|
rt_unref(rt);
|
|
goto bad;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* note that rt_gateway is a sockaddr_dl which contains the
|
|
* atm_pseudohdr data structure for this route. we currently
|
|
* don't need any rt_llinfo info (but will if we want to support
|
|
* ATM ARP [c.f. if_ether.c]).
|
|
*/
|
|
|
|
sdl = satocsdl((rt ? rt : rt0)->rt_gateway);
|
|
|
|
/*
|
|
* Check the address family and length is valid, the address
|
|
* is resolved; otherwise, try to resolve.
|
|
*/
|
|
|
|
if (sdl->sdl_family == AF_LINK && sdl->sdl_alen == sizeof(*desten)) {
|
|
memcpy(desten, CLLADDR(sdl), sdl->sdl_alen);
|
|
if (rt != NULL)
|
|
rt_unref(rt);
|
|
return (1); /* ok, go for it! */
|
|
}
|
|
|
|
if (rt != NULL)
|
|
rt_unref(rt);
|
|
|
|
/*
|
|
* we got an entry, but it doesn't have valid link address
|
|
* info in it (it is prob. the interface route, which has
|
|
* sdl_alen == 0). dump packet. (fall through to "bad").
|
|
*/
|
|
|
|
bad:
|
|
m_freem(m);
|
|
return (0);
|
|
}
|
|
#endif /* INET */
|