NetBSD/sys/net/link_proto.c

555 lines
13 KiB
C
Raw Normal View History

/* $NetBSD: link_proto.c,v 1.20 2014/07/31 13:21:33 rtr Exp $ */
Take steps to hide the radix_node implementation of the forwarding table from the forwarding table's users: Introduce rt_walktree() for walking the routing table and applying a function to each rtentry. Replace most rn_walktree() calls with it. Use rt_getkey()/rt_setkey() to get/set a route's destination. Keep a pointer to the sockaddr key in the rtentry, so that rtentry users do not have to grovel in the radix_node for the key. Add a RTM_GET method to rtrequest. Use that instead of radix_node lookups in, e.g., carp(4). Add sys/net/link_proto.c, which supplies sockaddr routines for link-layer socket addresses (sockaddr_dl). Cosmetic: Constify. KNF. Stop open-coding LIST_FOREACH, TAILQ_FOREACH, et cetera. Use NULL instead of 0 for null pointers. Use __arraycount(). Reduce gratuitous parenthesization. Stop using variadic arguments for rip6_output(), it is unnecessary. Remove the unnecessary rtentry member rt_genmask and the code to maintain it, since nothing actually used it. Make rt_maskedcopy() easier to read by using meaningful variable names. Extract a subroutine intern_netmask() for looking up a netmask in the masks table. Start converting backslash-ridden IPv6 macros in sys/netinet6/in6_var.h into inline subroutines that one can read without special eyeglasses. One functional change: when the kernel serves an RTM_GET, RTM_LOCK, or RTM_CHANGE request, it applies the netmask (if supplied) to a destination before searching for it in the forwarding table. I have changed sys/netinet/ip_carp.c, carp_setroute(), to remove the unlawful radix_node knowledge. Apart from the changes to carp(4), netiso, ATM, and strip(4), I have run the changes on three nodes in my wireless routing testbed, which involves IPv4 + IPv6 dynamic routing acrobatics, and it's working beautifully so far.
2007-07-20 00:48:52 +04:00
/*-
* Copyright (c) 1982, 1986, 1993
* 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.
* 3. 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.
*
* @(#)uipc_proto.c 8.2 (Berkeley) 2/14/95
*/
#include <sys/cdefs.h>
__KERNEL_RCSID(0, "$NetBSD: link_proto.c,v 1.20 2014/07/31 13:21:33 rtr Exp $");
Take steps to hide the radix_node implementation of the forwarding table from the forwarding table's users: Introduce rt_walktree() for walking the routing table and applying a function to each rtentry. Replace most rn_walktree() calls with it. Use rt_getkey()/rt_setkey() to get/set a route's destination. Keep a pointer to the sockaddr key in the rtentry, so that rtentry users do not have to grovel in the radix_node for the key. Add a RTM_GET method to rtrequest. Use that instead of radix_node lookups in, e.g., carp(4). Add sys/net/link_proto.c, which supplies sockaddr routines for link-layer socket addresses (sockaddr_dl). Cosmetic: Constify. KNF. Stop open-coding LIST_FOREACH, TAILQ_FOREACH, et cetera. Use NULL instead of 0 for null pointers. Use __arraycount(). Reduce gratuitous parenthesization. Stop using variadic arguments for rip6_output(), it is unnecessary. Remove the unnecessary rtentry member rt_genmask and the code to maintain it, since nothing actually used it. Make rt_maskedcopy() easier to read by using meaningful variable names. Extract a subroutine intern_netmask() for looking up a netmask in the masks table. Start converting backslash-ridden IPv6 macros in sys/netinet6/in6_var.h into inline subroutines that one can read without special eyeglasses. One functional change: when the kernel serves an RTM_GET, RTM_LOCK, or RTM_CHANGE request, it applies the netmask (if supplied) to a destination before searching for it in the forwarding table. I have changed sys/netinet/ip_carp.c, carp_setroute(), to remove the unlawful radix_node knowledge. Apart from the changes to carp(4), netiso, ATM, and strip(4), I have run the changes on three nodes in my wireless routing testbed, which involves IPv4 + IPv6 dynamic routing acrobatics, and it's working beautifully so far.
2007-07-20 00:48:52 +04:00
#include <sys/param.h>
#include <sys/socket.h>
#include <sys/protosw.h>
#include <sys/domain.h>
#include <sys/mbuf.h>
#include <sys/un.h>
#include <sys/socketvar.h>
#include <net/if.h>
#include <net/if_dl.h>
#include <net/raw_cb.h>
#include <net/route.h>
Take steps to hide the radix_node implementation of the forwarding table from the forwarding table's users: Introduce rt_walktree() for walking the routing table and applying a function to each rtentry. Replace most rn_walktree() calls with it. Use rt_getkey()/rt_setkey() to get/set a route's destination. Keep a pointer to the sockaddr key in the rtentry, so that rtentry users do not have to grovel in the radix_node for the key. Add a RTM_GET method to rtrequest. Use that instead of radix_node lookups in, e.g., carp(4). Add sys/net/link_proto.c, which supplies sockaddr routines for link-layer socket addresses (sockaddr_dl). Cosmetic: Constify. KNF. Stop open-coding LIST_FOREACH, TAILQ_FOREACH, et cetera. Use NULL instead of 0 for null pointers. Use __arraycount(). Reduce gratuitous parenthesization. Stop using variadic arguments for rip6_output(), it is unnecessary. Remove the unnecessary rtentry member rt_genmask and the code to maintain it, since nothing actually used it. Make rt_maskedcopy() easier to read by using meaningful variable names. Extract a subroutine intern_netmask() for looking up a netmask in the masks table. Start converting backslash-ridden IPv6 macros in sys/netinet6/in6_var.h into inline subroutines that one can read without special eyeglasses. One functional change: when the kernel serves an RTM_GET, RTM_LOCK, or RTM_CHANGE request, it applies the netmask (if supplied) to a destination before searching for it in the forwarding table. I have changed sys/netinet/ip_carp.c, carp_setroute(), to remove the unlawful radix_node knowledge. Apart from the changes to carp(4), netiso, ATM, and strip(4), I have run the changes on three nodes in my wireless routing testbed, which involves IPv4 + IPv6 dynamic routing acrobatics, and it's working beautifully so far.
2007-07-20 00:48:52 +04:00
static int sockaddr_dl_cmp(const struct sockaddr *, const struct sockaddr *);
static int link_attach(struct socket *, int);
static void link_detach(struct socket *);
static int link_accept(struct socket *, struct mbuf *);
static int link_bind(struct socket *, struct mbuf *);
static int link_listen(struct socket *);
static int link_connect(struct socket *, struct mbuf *);
static int link_disconnect(struct socket *);
static int link_shutdown(struct socket *);
static int link_abort(struct socket *);
static int link_ioctl(struct socket *, u_long, void *, struct ifnet *);
static int link_stat(struct socket *, struct stat *);
* split PRU_PEERADDR and PRU_SOCKADDR function out of pr_generic() usrreq switches and put into separate functions xxx_{peer,sock}addr(struct socket *, struct mbuf *). - KASSERT(solocked(so)) always in new functions even if request is not implemented - KASSERT(pcb != NULL) and KASSERT(nam) if the request is implemented and not for tcp. * for tcp roll #ifdef KPROF and #ifdef DEBUG code from tcp_usrreq() into easier to cut & paste functions tcp_debug_capture() and tcp_debug_trace() - functions provided by rmind - remaining use of PRU_{PEER,SOCK}ADDR #define to be removed in a future commit. * rename netbt functions to permit consistency of pru function names (as has been done with other requests already split out). - l2cap_{peer,sock}addr() -> l2cap_{peer,sock}_addr_pcb() - rfcomm_{peer,sock}addr() -> rfcomm_{peer,sock}_addr_pcb() - sco_{peer,sock}addr() -> sco_{peer,sock}_addr_pcb() * split/refactor do_sys_getsockname(lwp, fd, which, nam) into two functions do_sys_get{peer,sock}name(fd, nam). - move PRU_PEERADDR handling into do_sys_getpeername() from do_sys_getsockname() - have svr4_stream directly call do_sys_get{sock,peer}name() respectively instead of providing `which' & fix a DPRINTF string that incorrectly wrote "getpeername" when it meant "getsockname" - fix sys_getpeername() and sys_getsockname() to call do_sys_get{sock,peer}name() without `which' and `lwp' & adjust comments - bump kernel version for removal of lwp & which parameters from do_sys_getsockname() note: future cleanup to remove struct mbuf * abuse in xxx_{peer,sock}name() still to come, not done in this commit since it is easier to do post split. patch reviewed by rmind welcome to 6.99.47
2014-07-09 08:54:03 +04:00
static int link_peeraddr(struct socket *, struct mbuf *);
static int link_sockaddr(struct socket *, struct mbuf *);
static int link_recvoob(struct socket *, struct mbuf *, int);
static int link_sendoob(struct socket *, struct mbuf *, struct mbuf *);
static int link_usrreq(struct socket *, int, struct mbuf *, struct mbuf *,
struct mbuf *, struct lwp *);
static void link_init(void);
Take steps to hide the radix_node implementation of the forwarding table from the forwarding table's users: Introduce rt_walktree() for walking the routing table and applying a function to each rtentry. Replace most rn_walktree() calls with it. Use rt_getkey()/rt_setkey() to get/set a route's destination. Keep a pointer to the sockaddr key in the rtentry, so that rtentry users do not have to grovel in the radix_node for the key. Add a RTM_GET method to rtrequest. Use that instead of radix_node lookups in, e.g., carp(4). Add sys/net/link_proto.c, which supplies sockaddr routines for link-layer socket addresses (sockaddr_dl). Cosmetic: Constify. KNF. Stop open-coding LIST_FOREACH, TAILQ_FOREACH, et cetera. Use NULL instead of 0 for null pointers. Use __arraycount(). Reduce gratuitous parenthesization. Stop using variadic arguments for rip6_output(), it is unnecessary. Remove the unnecessary rtentry member rt_genmask and the code to maintain it, since nothing actually used it. Make rt_maskedcopy() easier to read by using meaningful variable names. Extract a subroutine intern_netmask() for looking up a netmask in the masks table. Start converting backslash-ridden IPv6 macros in sys/netinet6/in6_var.h into inline subroutines that one can read without special eyeglasses. One functional change: when the kernel serves an RTM_GET, RTM_LOCK, or RTM_CHANGE request, it applies the netmask (if supplied) to a destination before searching for it in the forwarding table. I have changed sys/netinet/ip_carp.c, carp_setroute(), to remove the unlawful radix_node knowledge. Apart from the changes to carp(4), netiso, ATM, and strip(4), I have run the changes on three nodes in my wireless routing testbed, which involves IPv4 + IPv6 dynamic routing acrobatics, and it's working beautifully so far.
2007-07-20 00:48:52 +04:00
/*
* Definitions of protocols supported in the link-layer domain.
*/
DOMAIN_DEFINE(linkdomain); /* forward define and add to link set */
static const struct pr_usrreqs link_usrreqs = {
.pr_attach = link_attach,
.pr_detach = link_detach,
.pr_accept = link_accept,
.pr_bind = link_bind,
.pr_listen = link_listen,
.pr_connect = link_connect,
.pr_disconnect = link_disconnect,
.pr_shutdown = link_shutdown,
.pr_abort = link_abort,
.pr_ioctl = link_ioctl,
.pr_stat = link_stat,
* split PRU_PEERADDR and PRU_SOCKADDR function out of pr_generic() usrreq switches and put into separate functions xxx_{peer,sock}addr(struct socket *, struct mbuf *). - KASSERT(solocked(so)) always in new functions even if request is not implemented - KASSERT(pcb != NULL) and KASSERT(nam) if the request is implemented and not for tcp. * for tcp roll #ifdef KPROF and #ifdef DEBUG code from tcp_usrreq() into easier to cut & paste functions tcp_debug_capture() and tcp_debug_trace() - functions provided by rmind - remaining use of PRU_{PEER,SOCK}ADDR #define to be removed in a future commit. * rename netbt functions to permit consistency of pru function names (as has been done with other requests already split out). - l2cap_{peer,sock}addr() -> l2cap_{peer,sock}_addr_pcb() - rfcomm_{peer,sock}addr() -> rfcomm_{peer,sock}_addr_pcb() - sco_{peer,sock}addr() -> sco_{peer,sock}_addr_pcb() * split/refactor do_sys_getsockname(lwp, fd, which, nam) into two functions do_sys_get{peer,sock}name(fd, nam). - move PRU_PEERADDR handling into do_sys_getpeername() from do_sys_getsockname() - have svr4_stream directly call do_sys_get{sock,peer}name() respectively instead of providing `which' & fix a DPRINTF string that incorrectly wrote "getpeername" when it meant "getsockname" - fix sys_getpeername() and sys_getsockname() to call do_sys_get{sock,peer}name() without `which' and `lwp' & adjust comments - bump kernel version for removal of lwp & which parameters from do_sys_getsockname() note: future cleanup to remove struct mbuf * abuse in xxx_{peer,sock}name() still to come, not done in this commit since it is easier to do post split. patch reviewed by rmind welcome to 6.99.47
2014-07-09 08:54:03 +04:00
.pr_peeraddr = link_peeraddr,
.pr_sockaddr = link_sockaddr,
.pr_recvoob = link_recvoob,
.pr_sendoob = link_sendoob,
.pr_generic = link_usrreq,
};
const struct protosw linksw[] = {
{ .pr_type = SOCK_DGRAM,
.pr_domain = &linkdomain,
.pr_protocol = 0, /* XXX */
.pr_flags = PR_ATOMIC|PR_ADDR|PR_PURGEIF,
.pr_input = NULL,
.pr_ctlinput = NULL,
.pr_ctloutput = NULL,
.pr_usrreqs = &link_usrreqs,
.pr_init = link_init,
},
};
Take steps to hide the radix_node implementation of the forwarding table from the forwarding table's users: Introduce rt_walktree() for walking the routing table and applying a function to each rtentry. Replace most rn_walktree() calls with it. Use rt_getkey()/rt_setkey() to get/set a route's destination. Keep a pointer to the sockaddr key in the rtentry, so that rtentry users do not have to grovel in the radix_node for the key. Add a RTM_GET method to rtrequest. Use that instead of radix_node lookups in, e.g., carp(4). Add sys/net/link_proto.c, which supplies sockaddr routines for link-layer socket addresses (sockaddr_dl). Cosmetic: Constify. KNF. Stop open-coding LIST_FOREACH, TAILQ_FOREACH, et cetera. Use NULL instead of 0 for null pointers. Use __arraycount(). Reduce gratuitous parenthesization. Stop using variadic arguments for rip6_output(), it is unnecessary. Remove the unnecessary rtentry member rt_genmask and the code to maintain it, since nothing actually used it. Make rt_maskedcopy() easier to read by using meaningful variable names. Extract a subroutine intern_netmask() for looking up a netmask in the masks table. Start converting backslash-ridden IPv6 macros in sys/netinet6/in6_var.h into inline subroutines that one can read without special eyeglasses. One functional change: when the kernel serves an RTM_GET, RTM_LOCK, or RTM_CHANGE request, it applies the netmask (if supplied) to a destination before searching for it in the forwarding table. I have changed sys/netinet/ip_carp.c, carp_setroute(), to remove the unlawful radix_node knowledge. Apart from the changes to carp(4), netiso, ATM, and strip(4), I have run the changes on three nodes in my wireless routing testbed, which involves IPv4 + IPv6 dynamic routing acrobatics, and it's working beautifully so far.
2007-07-20 00:48:52 +04:00
struct domain linkdomain = {
.dom_family = AF_LINK,
.dom_name = "link",
.dom_externalize = NULL,
.dom_dispose = NULL,
.dom_protosw = linksw,
.dom_protoswNPROTOSW = &linksw[__arraycount(linksw)],
Take steps to hide the radix_node implementation of the forwarding table from the forwarding table's users: Introduce rt_walktree() for walking the routing table and applying a function to each rtentry. Replace most rn_walktree() calls with it. Use rt_getkey()/rt_setkey() to get/set a route's destination. Keep a pointer to the sockaddr key in the rtentry, so that rtentry users do not have to grovel in the radix_node for the key. Add a RTM_GET method to rtrequest. Use that instead of radix_node lookups in, e.g., carp(4). Add sys/net/link_proto.c, which supplies sockaddr routines for link-layer socket addresses (sockaddr_dl). Cosmetic: Constify. KNF. Stop open-coding LIST_FOREACH, TAILQ_FOREACH, et cetera. Use NULL instead of 0 for null pointers. Use __arraycount(). Reduce gratuitous parenthesization. Stop using variadic arguments for rip6_output(), it is unnecessary. Remove the unnecessary rtentry member rt_genmask and the code to maintain it, since nothing actually used it. Make rt_maskedcopy() easier to read by using meaningful variable names. Extract a subroutine intern_netmask() for looking up a netmask in the masks table. Start converting backslash-ridden IPv6 macros in sys/netinet6/in6_var.h into inline subroutines that one can read without special eyeglasses. One functional change: when the kernel serves an RTM_GET, RTM_LOCK, or RTM_CHANGE request, it applies the netmask (if supplied) to a destination before searching for it in the forwarding table. I have changed sys/netinet/ip_carp.c, carp_setroute(), to remove the unlawful radix_node knowledge. Apart from the changes to carp(4), netiso, ATM, and strip(4), I have run the changes on three nodes in my wireless routing testbed, which involves IPv4 + IPv6 dynamic routing acrobatics, and it's working beautifully so far.
2007-07-20 00:48:52 +04:00
.dom_sockaddr_cmp = sockaddr_dl_cmp
};
static void
link_init(void)
{
return;
}
static int
link_control(struct socket *so, unsigned long cmd, void *data,
struct ifnet *ifp)
{
int error, s;
bool isactive, mkactive;
struct if_laddrreq *iflr;
union {
struct sockaddr sa;
struct sockaddr_dl sdl;
struct sockaddr_storage ss;
} u;
struct ifaddr *ifa;
const struct sockaddr_dl *asdl, *nsdl;
switch (cmd) {
case SIOCALIFADDR:
case SIOCDLIFADDR:
case SIOCGLIFADDR:
iflr = data;
if (iflr->addr.ss_family != AF_LINK)
return EINVAL;
asdl = satocsdl(sstocsa(&iflr->addr));
if (asdl->sdl_alen != ifp->if_addrlen)
return EINVAL;
if (sockaddr_dl_init(&u.sdl, sizeof(u.ss), ifp->if_index,
ifp->if_type, ifp->if_xname, strlen(ifp->if_xname),
CLLADDR(asdl), asdl->sdl_alen) == NULL)
return EINVAL;
if ((iflr->flags & IFLR_PREFIX) == 0)
;
else if (iflr->prefixlen != NBBY * ifp->if_addrlen)
return EINVAL; /* XXX match with prefix */
error = 0;
s = splnet();
IFADDR_FOREACH(ifa, ifp) {
if (sockaddr_cmp(&u.sa, ifa->ifa_addr) == 0)
break;
}
switch (cmd) {
case SIOCGLIFADDR:
if ((iflr->flags & IFLR_PREFIX) == 0) {
IFADDR_FOREACH(ifa, ifp) {
if (ifa->ifa_addr->sa_family == AF_LINK)
break;
}
}
if (ifa == NULL) {
error = EADDRNOTAVAIL;
break;
}
if (ifa == ifp->if_dl)
iflr->flags = IFLR_ACTIVE;
else
iflr->flags = 0;
*** Summary *** When a link-layer address changes (e.g., ifconfig ex0 link 02:de:ad:be:ef:02 active), send a gratuitous ARP and/or a Neighbor Advertisement to update the network-/link-layer address bindings on our LAN peers. Refuse a change of ethernet address to the address 00:00:00:00:00:00 or to any multicast/broadcast address. (Thanks matt@.) Reorder ifnet ioctl operations so that driver ioctls may inherit the functions of their "class"---ether_ioctl(), fddi_ioctl(), et cetera---and the class ioctls may inherit from the generic ioctl, ifioctl_common(), but both driver- and class-ioctls may override the generic behavior. Make network drivers share more code. Distinguish a "factory" link-layer address from others for the purposes of both protecting that address from deletion and computing EUI64. Return consistent, appropriate error codes from network drivers. Improve readability. KNF. *** Details *** In if_attach(), always initialize the interface ioctl routine, ifnet->if_ioctl, if the driver has not already initialized it. Delete if_ioctl == NULL tests everywhere else, because it cannot happen. In the ioctl routines of network interfaces, inherit common ioctl behaviors by calling either ifioctl_common() or whichever ioctl routine is appropriate for the class of interface---e.g., ether_ioctl() for ethernets. Stop (ab)using SIOCSIFADDR and start to use SIOCINITIFADDR. In the user->kernel interface, SIOCSIFADDR's argument was an ifreq, but on the protocol->ifnet interface, SIOCSIFADDR's argument was an ifaddr. That was confusing, and it would work against me as I make it possible for a network interface to overload most ioctls. On the protocol->ifnet interface, replace SIOCSIFADDR with SIOCINITIFADDR. In ifioctl(), return EPERM if userland tries to invoke SIOCINITIFADDR. In ifioctl(), give the interface the first shot at handling most interface ioctls, and give the protocol the second shot, instead of the other way around. Finally, let compatibility code (COMPAT_OSOCK) take a shot. Pull device initialization out of switch statements under SIOCINITIFADDR. For example, pull ..._init() out of any switch statement that looks like this: switch (...->sa_family) { case ...: ..._init(); ... break; ... default: ..._init(); ... break; } Rewrite many if-else clauses that handle all permutations of IFF_UP and IFF_RUNNING to use a switch statement, switch (x & (IFF_UP|IFF_RUNNING)) { case 0: ... break; case IFF_RUNNING: ... break; case IFF_UP: ... break; case IFF_UP|IFF_RUNNING: ... break; } unifdef lots of code containing #ifdef FreeBSD, #ifdef NetBSD, and #ifdef SIOCSIFMTU, especially in fwip(4) and in ndis(4). In ipw(4), remove an if_set_sadl() call that is out of place. In nfe(4), reuse the jumbo MTU logic in ether_ioctl(). Let ethernets register a callback for setting h/w state such as promiscuous mode and the multicast filter in accord with a change in the if_flags: ether_set_ifflags_cb() registers a callback that returns ENETRESET if the caller should reset the ethernet by calling if_init(), 0 on success, != 0 on failure. Pull common code from ex(4), gem(4), nfe(4), sip(4), tlp(4), vge(4) into ether_ioctl(), and register if_flags callbacks for those drivers. Return ENOTTY instead of EINVAL for inappropriate ioctls. In zyd(4), use ENXIO instead of ENOTTY to indicate that the device is not any longer attached. Add to if_set_sadl() a boolean 'factory' argument that indicates whether a link-layer address was assigned by the factory or some other source. In a comment, recommend using the factory address for generating an EUI64, and update in6_get_hw_ifid() to prefer a factory address to any other link-layer address. Add a routing message, RTM_LLINFO_UPD, that tells protocols to update the binding of network-layer addresses to link-layer addresses. Implement this message in IPv4 and IPv6 by sending a gratuitous ARP or a neighbor advertisement, respectively. Generate RTM_LLINFO_UPD messages on a change of an interface's link-layer address. In ether_ioctl(), do not let SIOCALIFADDR set a link-layer address that is broadcast/multicast or equal to 00:00:00:00:00:00. Make ether_ioctl() call ifioctl_common() to handle ioctls that it does not understand. In gif(4), initialize if_softc and use it, instead of assuming that the gif_softc and ifp overlap. Let ifioctl_common() handle SIOCGIFADDR. Sprinkle rtcache_invariants(), which checks on DIAGNOSTIC kernels that certain invariants on a struct route are satisfied. In agr(4), rewrite agr_ioctl_filter() to be a bit more explicit about the ioctls that we do not allow on an agr(4) member interface. bzero -> memset. Delete unnecessary casts to void *. Use sockaddr_in_init() and sockaddr_in6_init(). Compare pointers with NULL instead of "testing truth". Replace some instances of (type *)0 with NULL. Change some K&R prototypes to ANSI C, and join lines.
2008-11-07 03:20:01 +03:00
if (ifa == ifp->if_hwdl)
iflr->flags |= IFLR_FACTORY;
sockaddr_copy(sstosa(&iflr->addr), sizeof(iflr->addr),
ifa->ifa_addr);
break;
case SIOCDLIFADDR:
if (ifa == NULL)
error = EADDRNOTAVAIL;
*** Summary *** When a link-layer address changes (e.g., ifconfig ex0 link 02:de:ad:be:ef:02 active), send a gratuitous ARP and/or a Neighbor Advertisement to update the network-/link-layer address bindings on our LAN peers. Refuse a change of ethernet address to the address 00:00:00:00:00:00 or to any multicast/broadcast address. (Thanks matt@.) Reorder ifnet ioctl operations so that driver ioctls may inherit the functions of their "class"---ether_ioctl(), fddi_ioctl(), et cetera---and the class ioctls may inherit from the generic ioctl, ifioctl_common(), but both driver- and class-ioctls may override the generic behavior. Make network drivers share more code. Distinguish a "factory" link-layer address from others for the purposes of both protecting that address from deletion and computing EUI64. Return consistent, appropriate error codes from network drivers. Improve readability. KNF. *** Details *** In if_attach(), always initialize the interface ioctl routine, ifnet->if_ioctl, if the driver has not already initialized it. Delete if_ioctl == NULL tests everywhere else, because it cannot happen. In the ioctl routines of network interfaces, inherit common ioctl behaviors by calling either ifioctl_common() or whichever ioctl routine is appropriate for the class of interface---e.g., ether_ioctl() for ethernets. Stop (ab)using SIOCSIFADDR and start to use SIOCINITIFADDR. In the user->kernel interface, SIOCSIFADDR's argument was an ifreq, but on the protocol->ifnet interface, SIOCSIFADDR's argument was an ifaddr. That was confusing, and it would work against me as I make it possible for a network interface to overload most ioctls. On the protocol->ifnet interface, replace SIOCSIFADDR with SIOCINITIFADDR. In ifioctl(), return EPERM if userland tries to invoke SIOCINITIFADDR. In ifioctl(), give the interface the first shot at handling most interface ioctls, and give the protocol the second shot, instead of the other way around. Finally, let compatibility code (COMPAT_OSOCK) take a shot. Pull device initialization out of switch statements under SIOCINITIFADDR. For example, pull ..._init() out of any switch statement that looks like this: switch (...->sa_family) { case ...: ..._init(); ... break; ... default: ..._init(); ... break; } Rewrite many if-else clauses that handle all permutations of IFF_UP and IFF_RUNNING to use a switch statement, switch (x & (IFF_UP|IFF_RUNNING)) { case 0: ... break; case IFF_RUNNING: ... break; case IFF_UP: ... break; case IFF_UP|IFF_RUNNING: ... break; } unifdef lots of code containing #ifdef FreeBSD, #ifdef NetBSD, and #ifdef SIOCSIFMTU, especially in fwip(4) and in ndis(4). In ipw(4), remove an if_set_sadl() call that is out of place. In nfe(4), reuse the jumbo MTU logic in ether_ioctl(). Let ethernets register a callback for setting h/w state such as promiscuous mode and the multicast filter in accord with a change in the if_flags: ether_set_ifflags_cb() registers a callback that returns ENETRESET if the caller should reset the ethernet by calling if_init(), 0 on success, != 0 on failure. Pull common code from ex(4), gem(4), nfe(4), sip(4), tlp(4), vge(4) into ether_ioctl(), and register if_flags callbacks for those drivers. Return ENOTTY instead of EINVAL for inappropriate ioctls. In zyd(4), use ENXIO instead of ENOTTY to indicate that the device is not any longer attached. Add to if_set_sadl() a boolean 'factory' argument that indicates whether a link-layer address was assigned by the factory or some other source. In a comment, recommend using the factory address for generating an EUI64, and update in6_get_hw_ifid() to prefer a factory address to any other link-layer address. Add a routing message, RTM_LLINFO_UPD, that tells protocols to update the binding of network-layer addresses to link-layer addresses. Implement this message in IPv4 and IPv6 by sending a gratuitous ARP or a neighbor advertisement, respectively. Generate RTM_LLINFO_UPD messages on a change of an interface's link-layer address. In ether_ioctl(), do not let SIOCALIFADDR set a link-layer address that is broadcast/multicast or equal to 00:00:00:00:00:00. Make ether_ioctl() call ifioctl_common() to handle ioctls that it does not understand. In gif(4), initialize if_softc and use it, instead of assuming that the gif_softc and ifp overlap. Let ifioctl_common() handle SIOCGIFADDR. Sprinkle rtcache_invariants(), which checks on DIAGNOSTIC kernels that certain invariants on a struct route are satisfied. In agr(4), rewrite agr_ioctl_filter() to be a bit more explicit about the ioctls that we do not allow on an agr(4) member interface. bzero -> memset. Delete unnecessary casts to void *. Use sockaddr_in_init() and sockaddr_in6_init(). Compare pointers with NULL instead of "testing truth". Replace some instances of (type *)0 with NULL. Change some K&R prototypes to ANSI C, and join lines.
2008-11-07 03:20:01 +03:00
else if (ifa == ifp->if_dl || ifa == ifp->if_hwdl)
error = EBUSY;
else {
/* TBD routing socket */
rt_newaddrmsg(RTM_DELETE, ifa, 0, NULL);
ifa_remove(ifp, ifa);
}
break;
case SIOCALIFADDR:
if (ifa != NULL)
;
else if ((ifa = if_dl_create(ifp, &nsdl)) == NULL) {
error = ENOMEM;
break;
} else {
sockaddr_copy(ifa->ifa_addr,
ifa->ifa_addr->sa_len, &u.sa);
ifa_insert(ifp, ifa);
rt_newaddrmsg(RTM_ADD, ifa, 0, NULL);
}
mkactive = (iflr->flags & IFLR_ACTIVE) != 0;
isactive = (ifa == ifp->if_dl);
if (!isactive && mkactive) {
if_activate_sadl(ifp, ifa, nsdl);
rt_newaddrmsg(RTM_CHANGE, ifa, 0, NULL);
error = ENETRESET;
}
break;
}
splx(s);
if (error != ENETRESET)
return error;
else if ((ifp->if_flags & IFF_RUNNING) != 0 &&
ifp->if_init != NULL)
return (*ifp->if_init)(ifp);
else
return 0;
default:
return ENOTTY;
}
}
static int
link_attach(struct socket *so, int proto)
{
sosetlock(so);
KASSERT(solocked(so));
return 0;
}
static void
link_detach(struct socket *so)
{
KASSERT(solocked(so));
sofree(so);
}
static int
link_accept(struct socket *so, struct mbuf *nam)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
static int
link_bind(struct socket *so, struct mbuf *nam)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
static int
link_listen(struct socket *so)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
static int
link_connect(struct socket *so, struct mbuf *nam)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
static int
link_disconnect(struct socket *so)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
static int
link_shutdown(struct socket *so)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
static int
link_abort(struct socket *so)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
static int
link_ioctl(struct socket *so, u_long cmd, void *nam, struct ifnet *ifp)
{
return link_control(so, cmd, nam, ifp);
}
static int
link_stat(struct socket *so, struct stat *ub)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
* split PRU_PEERADDR and PRU_SOCKADDR function out of pr_generic() usrreq switches and put into separate functions xxx_{peer,sock}addr(struct socket *, struct mbuf *). - KASSERT(solocked(so)) always in new functions even if request is not implemented - KASSERT(pcb != NULL) and KASSERT(nam) if the request is implemented and not for tcp. * for tcp roll #ifdef KPROF and #ifdef DEBUG code from tcp_usrreq() into easier to cut & paste functions tcp_debug_capture() and tcp_debug_trace() - functions provided by rmind - remaining use of PRU_{PEER,SOCK}ADDR #define to be removed in a future commit. * rename netbt functions to permit consistency of pru function names (as has been done with other requests already split out). - l2cap_{peer,sock}addr() -> l2cap_{peer,sock}_addr_pcb() - rfcomm_{peer,sock}addr() -> rfcomm_{peer,sock}_addr_pcb() - sco_{peer,sock}addr() -> sco_{peer,sock}_addr_pcb() * split/refactor do_sys_getsockname(lwp, fd, which, nam) into two functions do_sys_get{peer,sock}name(fd, nam). - move PRU_PEERADDR handling into do_sys_getpeername() from do_sys_getsockname() - have svr4_stream directly call do_sys_get{sock,peer}name() respectively instead of providing `which' & fix a DPRINTF string that incorrectly wrote "getpeername" when it meant "getsockname" - fix sys_getpeername() and sys_getsockname() to call do_sys_get{sock,peer}name() without `which' and `lwp' & adjust comments - bump kernel version for removal of lwp & which parameters from do_sys_getsockname() note: future cleanup to remove struct mbuf * abuse in xxx_{peer,sock}name() still to come, not done in this commit since it is easier to do post split. patch reviewed by rmind welcome to 6.99.47
2014-07-09 08:54:03 +04:00
static int
link_peeraddr(struct socket *so, struct mbuf *nam)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
static int
link_sockaddr(struct socket *so, struct mbuf *nam)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
static int
link_recvoob(struct socket *so, struct mbuf *m, int flags)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
static int
link_sendoob(struct socket *so, struct mbuf *m, struct mbuf *control)
{
KASSERT(solocked(so));
return EOPNOTSUPP;
}
static int
link_usrreq(struct socket *so, int req, struct mbuf *m, struct mbuf *nam,
struct mbuf *control, struct lwp *l)
{
KASSERT(req != PRU_ATTACH);
KASSERT(req != PRU_DETACH);
KASSERT(req != PRU_ACCEPT);
KASSERT(req != PRU_BIND);
KASSERT(req != PRU_LISTEN);
KASSERT(req != PRU_CONNECT);
KASSERT(req != PRU_DISCONNECT);
KASSERT(req != PRU_SHUTDOWN);
KASSERT(req != PRU_ABORT);
KASSERT(req != PRU_CONTROL);
KASSERT(req != PRU_SENSE);
* split PRU_PEERADDR and PRU_SOCKADDR function out of pr_generic() usrreq switches and put into separate functions xxx_{peer,sock}addr(struct socket *, struct mbuf *). - KASSERT(solocked(so)) always in new functions even if request is not implemented - KASSERT(pcb != NULL) and KASSERT(nam) if the request is implemented and not for tcp. * for tcp roll #ifdef KPROF and #ifdef DEBUG code from tcp_usrreq() into easier to cut & paste functions tcp_debug_capture() and tcp_debug_trace() - functions provided by rmind - remaining use of PRU_{PEER,SOCK}ADDR #define to be removed in a future commit. * rename netbt functions to permit consistency of pru function names (as has been done with other requests already split out). - l2cap_{peer,sock}addr() -> l2cap_{peer,sock}_addr_pcb() - rfcomm_{peer,sock}addr() -> rfcomm_{peer,sock}_addr_pcb() - sco_{peer,sock}addr() -> sco_{peer,sock}_addr_pcb() * split/refactor do_sys_getsockname(lwp, fd, which, nam) into two functions do_sys_get{peer,sock}name(fd, nam). - move PRU_PEERADDR handling into do_sys_getpeername() from do_sys_getsockname() - have svr4_stream directly call do_sys_get{sock,peer}name() respectively instead of providing `which' & fix a DPRINTF string that incorrectly wrote "getpeername" when it meant "getsockname" - fix sys_getpeername() and sys_getsockname() to call do_sys_get{sock,peer}name() without `which' and `lwp' & adjust comments - bump kernel version for removal of lwp & which parameters from do_sys_getsockname() note: future cleanup to remove struct mbuf * abuse in xxx_{peer,sock}name() still to come, not done in this commit since it is easier to do post split. patch reviewed by rmind welcome to 6.99.47
2014-07-09 08:54:03 +04:00
KASSERT(req != PRU_PEERADDR);
KASSERT(req != PRU_SOCKADDR);
KASSERT(req != PRU_RCVOOB);
KASSERT(req != PRU_SENDOOB);
return EOPNOTSUPP;
}
Take steps to hide the radix_node implementation of the forwarding table from the forwarding table's users: Introduce rt_walktree() for walking the routing table and applying a function to each rtentry. Replace most rn_walktree() calls with it. Use rt_getkey()/rt_setkey() to get/set a route's destination. Keep a pointer to the sockaddr key in the rtentry, so that rtentry users do not have to grovel in the radix_node for the key. Add a RTM_GET method to rtrequest. Use that instead of radix_node lookups in, e.g., carp(4). Add sys/net/link_proto.c, which supplies sockaddr routines for link-layer socket addresses (sockaddr_dl). Cosmetic: Constify. KNF. Stop open-coding LIST_FOREACH, TAILQ_FOREACH, et cetera. Use NULL instead of 0 for null pointers. Use __arraycount(). Reduce gratuitous parenthesization. Stop using variadic arguments for rip6_output(), it is unnecessary. Remove the unnecessary rtentry member rt_genmask and the code to maintain it, since nothing actually used it. Make rt_maskedcopy() easier to read by using meaningful variable names. Extract a subroutine intern_netmask() for looking up a netmask in the masks table. Start converting backslash-ridden IPv6 macros in sys/netinet6/in6_var.h into inline subroutines that one can read without special eyeglasses. One functional change: when the kernel serves an RTM_GET, RTM_LOCK, or RTM_CHANGE request, it applies the netmask (if supplied) to a destination before searching for it in the forwarding table. I have changed sys/netinet/ip_carp.c, carp_setroute(), to remove the unlawful radix_node knowledge. Apart from the changes to carp(4), netiso, ATM, and strip(4), I have run the changes on three nodes in my wireless routing testbed, which involves IPv4 + IPv6 dynamic routing acrobatics, and it's working beautifully so far.
2007-07-20 00:48:52 +04:00
/* Compare the field at byte offsets [fieldstart, fieldend) in
* two memory regions, [l, l + llen) and [r, r + llen).
*/
static inline int
submemcmp(const void *l, const void *r,
const uint_fast8_t llen, const uint_fast8_t rlen,
const uint_fast8_t fieldstart, const uint_fast8_t fieldend)
{
uint_fast8_t cmpend, minlen;
const uint8_t *lb = l, *rb = r;
int rc;
minlen = MIN(llen, rlen);
/* The field is missing from one region. The shorter region is the
* lesser region.
*/
if (fieldstart >= minlen)
return llen - rlen;
/* Two empty, present fields are always equal. */
if (fieldstart > fieldend)
return 0;
cmpend = MIN(fieldend, minlen);
rc = memcmp(&lb[fieldstart], &rb[fieldstart], cmpend - fieldstart);
if (rc != 0)
return rc;
/* If one or both fields are truncated, then the shorter is the lesser
* field.
*/
if (minlen < fieldend)
return llen - rlen;
/* Fields are full-length and equal. The fields are equal. */
return 0;
}
uint8_t
sockaddr_dl_measure(uint8_t namelen, uint8_t addrlen)
{
return offsetof(struct sockaddr_dl, sdl_data[namelen + addrlen]);
}
struct sockaddr *
sockaddr_dl_alloc(uint16_t ifindex, uint8_t type,
const void *name, uint8_t namelen, const void *addr, uint8_t addrlen,
int flags)
{
struct sockaddr *sa;
socklen_t len;
len = sockaddr_dl_measure(namelen, addrlen);
sa = sockaddr_alloc(AF_LINK, len, flags);
if (sa == NULL)
return NULL;
if (sockaddr_dl_init(satosdl(sa), len, ifindex, type, name, namelen,
addr, addrlen) == NULL) {
sockaddr_free(sa);
return NULL;
}
return sa;
}
struct sockaddr_dl *
sockaddr_dl_init(struct sockaddr_dl *sdl, socklen_t socklen, uint16_t ifindex,
uint8_t type, const void *name, uint8_t namelen, const void *addr,
uint8_t addrlen)
{
socklen_t len;
sdl->sdl_family = AF_LINK;
sdl->sdl_slen = 0;
len = sockaddr_dl_measure(namelen, addrlen);
if (len > socklen) {
sdl->sdl_len = socklen;
#ifdef DIAGNOSTIC
printf("%s: too long: %u > %u\n", __func__, (u_int)len,
(u_int)socklen);
#endif
return NULL;
}
sdl->sdl_len = len;
sdl->sdl_index = ifindex;
sdl->sdl_type = type;
memset(&sdl->sdl_data[0], 0, namelen + addrlen);
if (name != NULL) {
memcpy(&sdl->sdl_data[0], name, namelen);
sdl->sdl_nlen = namelen;
} else
sdl->sdl_nlen = 0;
if (addr != NULL) {
memcpy(&sdl->sdl_data[sdl->sdl_nlen], addr, addrlen);
sdl->sdl_alen = addrlen;
} else
sdl->sdl_alen = 0;
return sdl;
}
Take steps to hide the radix_node implementation of the forwarding table from the forwarding table's users: Introduce rt_walktree() for walking the routing table and applying a function to each rtentry. Replace most rn_walktree() calls with it. Use rt_getkey()/rt_setkey() to get/set a route's destination. Keep a pointer to the sockaddr key in the rtentry, so that rtentry users do not have to grovel in the radix_node for the key. Add a RTM_GET method to rtrequest. Use that instead of radix_node lookups in, e.g., carp(4). Add sys/net/link_proto.c, which supplies sockaddr routines for link-layer socket addresses (sockaddr_dl). Cosmetic: Constify. KNF. Stop open-coding LIST_FOREACH, TAILQ_FOREACH, et cetera. Use NULL instead of 0 for null pointers. Use __arraycount(). Reduce gratuitous parenthesization. Stop using variadic arguments for rip6_output(), it is unnecessary. Remove the unnecessary rtentry member rt_genmask and the code to maintain it, since nothing actually used it. Make rt_maskedcopy() easier to read by using meaningful variable names. Extract a subroutine intern_netmask() for looking up a netmask in the masks table. Start converting backslash-ridden IPv6 macros in sys/netinet6/in6_var.h into inline subroutines that one can read without special eyeglasses. One functional change: when the kernel serves an RTM_GET, RTM_LOCK, or RTM_CHANGE request, it applies the netmask (if supplied) to a destination before searching for it in the forwarding table. I have changed sys/netinet/ip_carp.c, carp_setroute(), to remove the unlawful radix_node knowledge. Apart from the changes to carp(4), netiso, ATM, and strip(4), I have run the changes on three nodes in my wireless routing testbed, which involves IPv4 + IPv6 dynamic routing acrobatics, and it's working beautifully so far.
2007-07-20 00:48:52 +04:00
static int
sockaddr_dl_cmp(const struct sockaddr *sa1, const struct sockaddr *sa2)
{
int rc;
const uint_fast8_t indexofs = offsetof(struct sockaddr_dl, sdl_index);
const uint_fast8_t nlenofs = offsetof(struct sockaddr_dl, sdl_nlen);
uint_fast8_t dataofs = offsetof(struct sockaddr_dl, sdl_data[0]);
const struct sockaddr_dl *sdl1, *sdl2;
sdl1 = satocsdl(sa1);
sdl2 = satocsdl(sa2);
rc = submemcmp(sdl1, sdl2, sdl1->sdl_len, sdl2->sdl_len,
indexofs, nlenofs);
if (rc != 0)
return rc;
rc = submemcmp(sdl1, sdl2, sdl1->sdl_len, sdl2->sdl_len,
dataofs, dataofs + MIN(sdl1->sdl_nlen, sdl2->sdl_nlen));
if (rc != 0)
return rc;
if (sdl1->sdl_nlen != sdl2->sdl_nlen)
return sdl1->sdl_nlen - sdl2->sdl_nlen;
dataofs += sdl1->sdl_nlen;
rc = submemcmp(sdl1, sdl2, sdl1->sdl_len, sdl2->sdl_len,
dataofs, dataofs + MIN(sdl1->sdl_alen, sdl2->sdl_alen));
if (rc != 0)
return rc;
if (sdl1->sdl_alen != sdl2->sdl_alen)
return sdl1->sdl_alen - sdl2->sdl_alen;
dataofs += sdl1->sdl_alen;
rc = submemcmp(sdl1, sdl2, sdl1->sdl_len, sdl2->sdl_len,
dataofs, dataofs + MIN(sdl1->sdl_slen, sdl2->sdl_slen));
if (sdl1->sdl_slen != sdl2->sdl_slen)
return sdl1->sdl_slen - sdl2->sdl_slen;
return sdl1->sdl_len - sdl2->sdl_len;
}
struct sockaddr_dl *
sockaddr_dl_setaddr(struct sockaddr_dl *sdl, socklen_t socklen,
const void *addr, uint8_t addrlen)
{
socklen_t len;
len = sockaddr_dl_measure(sdl->sdl_nlen, addrlen);
if (len > socklen) {
#ifdef DIAGNOSTIC
printf("%s: too long: %u > %u\n", __func__, (u_int)len,
(u_int)socklen);
#endif
return NULL;
}
memcpy(&sdl->sdl_data[sdl->sdl_nlen], addr, addrlen);
sdl->sdl_alen = addrlen;
sdl->sdl_len = len;
return sdl;
}