diff --git a/sys/net/if_spppsubr.c b/sys/net/if_spppsubr.c
index 5a18147f14a7..fbf7b0ea8f4c 100644
--- a/sys/net/if_spppsubr.c
+++ b/sys/net/if_spppsubr.c
@@ -1,5413 +1,5417 @@
/*
* Synchronous PPP/Cisco/Frame Relay link level subroutines.
* Keepalive protocol implemented in both Cisco and PPP modes.
*/
/*-
* Copyright (C) 1994-2000 Cronyx Engineering.
* Author: Serge Vakulenko, <vak@cronyx.ru>
*
* Heavily revamped to conform to RFC 1661.
* Copyright (C) 1997, 2001 Joerg Wunsch.
*
* This software is distributed with NO WARRANTIES, not even the implied
* warranties for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
*
* Authors grant any other persons or organisations permission to use
* or modify this software as long as this message is kept with the software,
* all derivative works or modified versions.
*
* From: Version 2.4, Thu Apr 30 17:17:21 MSD 1997
*
* $FreeBSD$
*/
#include <sys/param.h>
#include "opt_inet.h"
#include "opt_inet6.h"
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/module.h>
#include <sys/rmlock.h>
#include <sys/sockio.h>
#include <sys/socket.h>
#include <sys/syslog.h>
#include <sys/random.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/md5.h>
#include <net/if.h>
#include <net/if_var.h>
#include <net/netisr.h>
#include <net/if_types.h>
#include <net/route.h>
#include <net/vnet.h>
#include <netinet/in.h>
+#include <netinet/in_var.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <net/slcompress.h>
#include <machine/stdarg.h>
#include <netinet/in_var.h>
#ifdef INET
#include <netinet/ip.h>
#include <netinet/tcp.h>
#endif
#ifdef INET6
#include <netinet6/scope6_var.h>
#endif
#include <netinet/if_ether.h>
#include <net/if_sppp.h>
#define IOCTL_CMD_T u_long
#define MAXALIVECNT 3 /* max. alive packets */
/*
* Interface flags that can be set in an ifconfig command.
*
* Setting link0 will make the link passive, i.e. it will be marked
* as being administrative openable, but won't be opened to begin
* with. Incoming calls will be answered, or subsequent calls with
* -link1 will cause the administrative open of the LCP layer.
*
* Setting link1 will cause the link to auto-dial only as packets
* arrive to be sent.
*
* Setting IFF_DEBUG will syslog the option negotiation and state
* transitions at level kern.debug. Note: all logs consistently look
* like
*
* <if-name><unit>: <proto-name> <additional info...>
*
* with <if-name><unit> being something like "bppp0", and <proto-name>
* being one of "lcp", "ipcp", "cisco", "chap", "pap", etc.
*/
#define IFF_PASSIVE IFF_LINK0 /* wait passively for connection */
#define IFF_AUTO IFF_LINK1 /* auto-dial on output */
#define IFF_CISCO IFF_LINK2 /* auto-dial on output */
#define PPP_ALLSTATIONS 0xff /* All-Stations broadcast address */
#define PPP_UI 0x03 /* Unnumbered Information */
#define PPP_IP 0x0021 /* Internet Protocol */
#define PPP_ISO 0x0023 /* ISO OSI Protocol */
#define PPP_XNS 0x0025 /* Xerox NS Protocol */
#define PPP_IPX 0x002b /* Novell IPX Protocol */
#define PPP_VJ_COMP 0x002d /* VJ compressed TCP/IP */
#define PPP_VJ_UCOMP 0x002f /* VJ uncompressed TCP/IP */
#define PPP_IPV6 0x0057 /* Internet Protocol Version 6 */
#define PPP_LCP 0xc021 /* Link Control Protocol */
#define PPP_PAP 0xc023 /* Password Authentication Protocol */
#define PPP_CHAP 0xc223 /* Challenge-Handshake Auth Protocol */
#define PPP_IPCP 0x8021 /* Internet Protocol Control Protocol */
#define PPP_IPV6CP 0x8057 /* IPv6 Control Protocol */
#define CONF_REQ 1 /* PPP configure request */
#define CONF_ACK 2 /* PPP configure acknowledge */
#define CONF_NAK 3 /* PPP configure negative ack */
#define CONF_REJ 4 /* PPP configure reject */
#define TERM_REQ 5 /* PPP terminate request */
#define TERM_ACK 6 /* PPP terminate acknowledge */
#define CODE_REJ 7 /* PPP code reject */
#define PROTO_REJ 8 /* PPP protocol reject */
#define ECHO_REQ 9 /* PPP echo request */
#define ECHO_REPLY 10 /* PPP echo reply */
#define DISC_REQ 11 /* PPP discard request */
#define LCP_OPT_MRU 1 /* maximum receive unit */
#define LCP_OPT_ASYNC_MAP 2 /* async control character map */
#define LCP_OPT_AUTH_PROTO 3 /* authentication protocol */
#define LCP_OPT_QUAL_PROTO 4 /* quality protocol */
#define LCP_OPT_MAGIC 5 /* magic number */
#define LCP_OPT_RESERVED 6 /* reserved */
#define LCP_OPT_PROTO_COMP 7 /* protocol field compression */
#define LCP_OPT_ADDR_COMP 8 /* address/control field compression */
#define IPCP_OPT_ADDRESSES 1 /* both IP addresses; deprecated */
#define IPCP_OPT_COMPRESSION 2 /* IP compression protocol (VJ) */
#define IPCP_OPT_ADDRESS 3 /* local IP address */
#define IPV6CP_OPT_IFID 1 /* interface identifier */
#define IPV6CP_OPT_COMPRESSION 2 /* IPv6 compression protocol */
#define IPCP_COMP_VJ 0x2d /* Code for VJ compression */
#define PAP_REQ 1 /* PAP name/password request */
#define PAP_ACK 2 /* PAP acknowledge */
#define PAP_NAK 3 /* PAP fail */
#define CHAP_CHALLENGE 1 /* CHAP challenge request */
#define CHAP_RESPONSE 2 /* CHAP challenge response */
#define CHAP_SUCCESS 3 /* CHAP response ok */
#define CHAP_FAILURE 4 /* CHAP response failed */
#define CHAP_MD5 5 /* hash algorithm - MD5 */
#define CISCO_MULTICAST 0x8f /* Cisco multicast address */
#define CISCO_UNICAST 0x0f /* Cisco unicast address */
#define CISCO_KEEPALIVE 0x8035 /* Cisco keepalive protocol */
#define CISCO_ADDR_REQ 0 /* Cisco address request */
#define CISCO_ADDR_REPLY 1 /* Cisco address reply */
#define CISCO_KEEPALIVE_REQ 2 /* Cisco keepalive request */
/* states are named and numbered according to RFC 1661 */
#define STATE_INITIAL 0
#define STATE_STARTING 1
#define STATE_CLOSED 2
#define STATE_STOPPED 3
#define STATE_CLOSING 4
#define STATE_STOPPING 5
#define STATE_REQ_SENT 6
#define STATE_ACK_RCVD 7
#define STATE_ACK_SENT 8
#define STATE_OPENED 9
static MALLOC_DEFINE(M_SPPP, "sppp", "synchronous PPP interface internals");
struct ppp_header {
u_char address;
u_char control;
u_short protocol;
} __packed;
#define PPP_HEADER_LEN sizeof (struct ppp_header)
struct lcp_header {
u_char type;
u_char ident;
u_short len;
} __packed;
#define LCP_HEADER_LEN sizeof (struct lcp_header)
struct cisco_packet {
u_long type;
u_long par1;
u_long par2;
u_short rel;
u_short time0;
u_short time1;
} __packed;
#define CISCO_PACKET_LEN sizeof (struct cisco_packet)
/*
* We follow the spelling and capitalization of RFC 1661 here, to make
* it easier comparing with the standard. Please refer to this RFC in
* case you can't make sense out of these abbreviation; it will also
* explain the semantics related to the various events and actions.
*/
struct cp {
u_short proto; /* PPP control protocol number */
u_char protoidx; /* index into state table in struct sppp */
u_char flags;
#define CP_LCP 0x01 /* this is the LCP */
#define CP_AUTH 0x02 /* this is an authentication protocol */
#define CP_NCP 0x04 /* this is a NCP */
#define CP_QUAL 0x08 /* this is a quality reporting protocol */
const char *name; /* name of this control protocol */
/* event handlers */
void (*Up)(struct sppp *sp);
void (*Down)(struct sppp *sp);
void (*Open)(struct sppp *sp);
void (*Close)(struct sppp *sp);
void (*TO)(void *sp);
int (*RCR)(struct sppp *sp, struct lcp_header *h, int len);
void (*RCN_rej)(struct sppp *sp, struct lcp_header *h, int len);
void (*RCN_nak)(struct sppp *sp, struct lcp_header *h, int len);
/* actions */
void (*tlu)(struct sppp *sp);
void (*tld)(struct sppp *sp);
void (*tls)(struct sppp *sp);
void (*tlf)(struct sppp *sp);
void (*scr)(struct sppp *sp);
};
#define SPP_FMT "%s: "
#define SPP_ARGS(ifp) (ifp)->if_xname
#define SPPP_LOCK(sp) mtx_lock (&(sp)->mtx)
#define SPPP_UNLOCK(sp) mtx_unlock (&(sp)->mtx)
#define SPPP_LOCK_ASSERT(sp) mtx_assert (&(sp)->mtx, MA_OWNED)
#define SPPP_LOCK_OWNED(sp) mtx_owned (&(sp)->mtx)
#ifdef INET
/*
* The following disgusting hack gets around the problem that IP TOS
* can't be set yet. We want to put "interactive" traffic on a high
* priority queue. To decide if traffic is interactive, we check that
* a) it is TCP and b) one of its ports is telnet, rlogin or ftp control.
*
* XXX is this really still necessary? - joerg -
*/
static const u_short interactive_ports[8] = {
0, 513, 0, 0,
0, 21, 0, 23,
};
#define INTERACTIVE(p) (interactive_ports[(p) & 7] == (p))
#endif
/* almost every function needs these */
#define STDDCL \
struct ifnet *ifp = SP2IFP(sp); \
int debug = ifp->if_flags & IFF_DEBUG
static int sppp_output(struct ifnet *ifp, struct mbuf *m,
const struct sockaddr *dst, struct route *ro);
static void sppp_cisco_send(struct sppp *sp, int type, long par1, long par2);
static void sppp_cisco_input(struct sppp *sp, struct mbuf *m);
static void sppp_cp_input(const struct cp *cp, struct sppp *sp,
struct mbuf *m);
static void sppp_cp_send(struct sppp *sp, u_short proto, u_char type,
u_char ident, u_short len, void *data);
/* static void sppp_cp_timeout(void *arg); */
static void sppp_cp_change_state(const struct cp *cp, struct sppp *sp,
int newstate);
static void sppp_auth_send(const struct cp *cp,
struct sppp *sp, unsigned int type, unsigned int id,
...);
static void sppp_up_event(const struct cp *cp, struct sppp *sp);
static void sppp_down_event(const struct cp *cp, struct sppp *sp);
static void sppp_open_event(const struct cp *cp, struct sppp *sp);
static void sppp_close_event(const struct cp *cp, struct sppp *sp);
static void sppp_to_event(const struct cp *cp, struct sppp *sp);
static void sppp_null(struct sppp *sp);
static void sppp_pp_up(struct sppp *sp);
static void sppp_pp_down(struct sppp *sp);
static void sppp_lcp_init(struct sppp *sp);
static void sppp_lcp_up(struct sppp *sp);
static void sppp_lcp_down(struct sppp *sp);
static void sppp_lcp_open(struct sppp *sp);
static void sppp_lcp_close(struct sppp *sp);
static void sppp_lcp_TO(void *sp);
static int sppp_lcp_RCR(struct sppp *sp, struct lcp_header *h, int len);
static void sppp_lcp_RCN_rej(struct sppp *sp, struct lcp_header *h, int len);
static void sppp_lcp_RCN_nak(struct sppp *sp, struct lcp_header *h, int len);
static void sppp_lcp_tlu(struct sppp *sp);
static void sppp_lcp_tld(struct sppp *sp);
static void sppp_lcp_tls(struct sppp *sp);
static void sppp_lcp_tlf(struct sppp *sp);
static void sppp_lcp_scr(struct sppp *sp);
static void sppp_lcp_check_and_close(struct sppp *sp);
static int sppp_ncp_check(struct sppp *sp);
static void sppp_ipcp_init(struct sppp *sp);
static void sppp_ipcp_up(struct sppp *sp);
static void sppp_ipcp_down(struct sppp *sp);
static void sppp_ipcp_open(struct sppp *sp);
static void sppp_ipcp_close(struct sppp *sp);
static void sppp_ipcp_TO(void *sp);
static int sppp_ipcp_RCR(struct sppp *sp, struct lcp_header *h, int len);
static void sppp_ipcp_RCN_rej(struct sppp *sp, struct lcp_header *h, int len);
static void sppp_ipcp_RCN_nak(struct sppp *sp, struct lcp_header *h, int len);
static void sppp_ipcp_tlu(struct sppp *sp);
static void sppp_ipcp_tld(struct sppp *sp);
static void sppp_ipcp_tls(struct sppp *sp);
static void sppp_ipcp_tlf(struct sppp *sp);
static void sppp_ipcp_scr(struct sppp *sp);
static void sppp_ipv6cp_init(struct sppp *sp);
static void sppp_ipv6cp_up(struct sppp *sp);
static void sppp_ipv6cp_down(struct sppp *sp);
static void sppp_ipv6cp_open(struct sppp *sp);
static void sppp_ipv6cp_close(struct sppp *sp);
static void sppp_ipv6cp_TO(void *sp);
static int sppp_ipv6cp_RCR(struct sppp *sp, struct lcp_header *h, int len);
static void sppp_ipv6cp_RCN_rej(struct sppp *sp, struct lcp_header *h, int len);
static void sppp_ipv6cp_RCN_nak(struct sppp *sp, struct lcp_header *h, int len);
static void sppp_ipv6cp_tlu(struct sppp *sp);
static void sppp_ipv6cp_tld(struct sppp *sp);
static void sppp_ipv6cp_tls(struct sppp *sp);
static void sppp_ipv6cp_tlf(struct sppp *sp);
static void sppp_ipv6cp_scr(struct sppp *sp);
static void sppp_pap_input(struct sppp *sp, struct mbuf *m);
static void sppp_pap_init(struct sppp *sp);
static void sppp_pap_open(struct sppp *sp);
static void sppp_pap_close(struct sppp *sp);
static void sppp_pap_TO(void *sp);
static void sppp_pap_my_TO(void *sp);
static void sppp_pap_tlu(struct sppp *sp);
static void sppp_pap_tld(struct sppp *sp);
static void sppp_pap_scr(struct sppp *sp);
static void sppp_chap_input(struct sppp *sp, struct mbuf *m);
static void sppp_chap_init(struct sppp *sp);
static void sppp_chap_open(struct sppp *sp);
static void sppp_chap_close(struct sppp *sp);
static void sppp_chap_TO(void *sp);
static void sppp_chap_tlu(struct sppp *sp);
static void sppp_chap_tld(struct sppp *sp);
static void sppp_chap_scr(struct sppp *sp);
static const char *sppp_auth_type_name(u_short proto, u_char type);
static const char *sppp_cp_type_name(u_char type);
#ifdef INET
static const char *sppp_dotted_quad(u_long addr);
static const char *sppp_ipcp_opt_name(u_char opt);
#endif
#ifdef INET6
static const char *sppp_ipv6cp_opt_name(u_char opt);
#endif
static const char *sppp_lcp_opt_name(u_char opt);
static const char *sppp_phase_name(enum ppp_phase phase);
static const char *sppp_proto_name(u_short proto);
static const char *sppp_state_name(int state);
static int sppp_params(struct sppp *sp, u_long cmd, void *data);
static int sppp_strnlen(u_char *p, int max);
static void sppp_keepalive(void *dummy);
static void sppp_phase_network(struct sppp *sp);
static void sppp_print_bytes(const u_char *p, u_short len);
static void sppp_print_string(const char *p, u_short len);
static void sppp_qflush(struct ifqueue *ifq);
#ifdef INET
static void sppp_set_ip_addr(struct sppp *sp, u_long src);
#endif
#ifdef INET6
static void sppp_get_ip6_addrs(struct sppp *sp, struct in6_addr *src,
struct in6_addr *dst, struct in6_addr *srcmask);
#ifdef IPV6CP_MYIFID_DYN
static void sppp_set_ip6_addr(struct sppp *sp, const struct in6_addr *src);
static void sppp_gen_ip6_addr(struct sppp *sp, const struct in6_addr *src);
#endif
static void sppp_suggest_ip6_addr(struct sppp *sp, struct in6_addr *src);
#endif
/* if_start () wrapper */
static void sppp_ifstart (struct ifnet *ifp);
/* our control protocol descriptors */
static const struct cp lcp = {
PPP_LCP, IDX_LCP, CP_LCP, "lcp",
sppp_lcp_up, sppp_lcp_down, sppp_lcp_open, sppp_lcp_close,
sppp_lcp_TO, sppp_lcp_RCR, sppp_lcp_RCN_rej, sppp_lcp_RCN_nak,
sppp_lcp_tlu, sppp_lcp_tld, sppp_lcp_tls, sppp_lcp_tlf,
sppp_lcp_scr
};
static const struct cp ipcp = {
PPP_IPCP, IDX_IPCP,
#ifdef INET /* don't run IPCP if there's no IPv4 support */
CP_NCP,
#else
0,
#endif
"ipcp",
sppp_ipcp_up, sppp_ipcp_down, sppp_ipcp_open, sppp_ipcp_close,
sppp_ipcp_TO, sppp_ipcp_RCR, sppp_ipcp_RCN_rej, sppp_ipcp_RCN_nak,
sppp_ipcp_tlu, sppp_ipcp_tld, sppp_ipcp_tls, sppp_ipcp_tlf,
sppp_ipcp_scr
};
static const struct cp ipv6cp = {
PPP_IPV6CP, IDX_IPV6CP,
#ifdef INET6 /*don't run IPv6CP if there's no IPv6 support*/
CP_NCP,
#else
0,
#endif
"ipv6cp",
sppp_ipv6cp_up, sppp_ipv6cp_down, sppp_ipv6cp_open, sppp_ipv6cp_close,
sppp_ipv6cp_TO, sppp_ipv6cp_RCR, sppp_ipv6cp_RCN_rej, sppp_ipv6cp_RCN_nak,
sppp_ipv6cp_tlu, sppp_ipv6cp_tld, sppp_ipv6cp_tls, sppp_ipv6cp_tlf,
sppp_ipv6cp_scr
};
static const struct cp pap = {
PPP_PAP, IDX_PAP, CP_AUTH, "pap",
sppp_null, sppp_null, sppp_pap_open, sppp_pap_close,
sppp_pap_TO, 0, 0, 0,
sppp_pap_tlu, sppp_pap_tld, sppp_null, sppp_null,
sppp_pap_scr
};
static const struct cp chap = {
PPP_CHAP, IDX_CHAP, CP_AUTH, "chap",
sppp_null, sppp_null, sppp_chap_open, sppp_chap_close,
sppp_chap_TO, 0, 0, 0,
sppp_chap_tlu, sppp_chap_tld, sppp_null, sppp_null,
sppp_chap_scr
};
static const struct cp *cps[IDX_COUNT] = {
&lcp, /* IDX_LCP */
&ipcp, /* IDX_IPCP */
&ipv6cp, /* IDX_IPV6CP */
&pap, /* IDX_PAP */
&chap, /* IDX_CHAP */
};
static void*
sppp_alloc(u_char type, struct ifnet *ifp)
{
struct sppp *sp;
sp = malloc(sizeof(struct sppp), M_SPPP, M_WAITOK | M_ZERO);
sp->pp_ifp = ifp;
return (sp);
}
static void
sppp_free(void *com, u_char type)
{
free(com, M_SPPP);
}
static int
sppp_modevent(module_t mod, int type, void *unused)
{
switch (type) {
case MOD_LOAD:
/*
* XXX: should probably be IFT_SPPP, but it's fairly
* harmless to allocate struct sppp's for non-sppp
* interfaces.
*/
if_register_com_alloc(IFT_PPP, sppp_alloc, sppp_free);
break;
case MOD_UNLOAD:
/* if_deregister_com_alloc(IFT_PPP); */
return EACCES;
default:
return EOPNOTSUPP;
}
return 0;
}
static moduledata_t spppmod = {
"sppp",
sppp_modevent,
0
};
MODULE_VERSION(sppp, 1);
DECLARE_MODULE(sppp, spppmod, SI_SUB_DRIVERS, SI_ORDER_ANY);
/*
* Exported functions, comprising our interface to the lower layer.
*/
/*
* Process the received packet.
*/
void
sppp_input(struct ifnet *ifp, struct mbuf *m)
{
struct ppp_header *h;
int isr = -1;
struct sppp *sp = IFP2SP(ifp);
int debug, do_account = 0;
#ifdef INET
int hlen, vjlen;
u_char *iphdr;
#endif
SPPP_LOCK(sp);
debug = ifp->if_flags & IFF_DEBUG;
if (ifp->if_flags & IFF_UP)
/* Count received bytes, add FCS and one flag */
if_inc_counter(ifp, IFCOUNTER_IBYTES, m->m_pkthdr.len + 3);
if (m->m_pkthdr.len <= PPP_HEADER_LEN) {
/* Too small packet, drop it. */
if (debug)
log(LOG_DEBUG,
SPP_FMT "input packet is too small, %d bytes\n",
SPP_ARGS(ifp), m->m_pkthdr.len);
drop:
m_freem (m);
SPPP_UNLOCK(sp);
drop2:
if_inc_counter(ifp, IFCOUNTER_IERRORS, 1);
if_inc_counter(ifp, IFCOUNTER_IQDROPS, 1);
return;
}
if (sp->pp_mode == PP_FR) {
sppp_fr_input (sp, m);
SPPP_UNLOCK(sp);
return;
}
/* Get PPP header. */
h = mtod (m, struct ppp_header*);
m_adj (m, PPP_HEADER_LEN);
switch (h->address) {
case PPP_ALLSTATIONS:
if (h->control != PPP_UI)
goto invalid;
if (sp->pp_mode == IFF_CISCO) {
if (debug)
log(LOG_DEBUG,
SPP_FMT "PPP packet in Cisco mode "
"<addr=0x%x ctrl=0x%x proto=0x%x>\n",
SPP_ARGS(ifp),
h->address, h->control, ntohs(h->protocol));
goto drop;
}
switch (ntohs (h->protocol)) {
default:
if (debug)
log(LOG_DEBUG,
SPP_FMT "rejecting protocol "
"<addr=0x%x ctrl=0x%x proto=0x%x>\n",
SPP_ARGS(ifp),
h->address, h->control, ntohs(h->protocol));
if (sp->state[IDX_LCP] == STATE_OPENED)
sppp_cp_send (sp, PPP_LCP, PROTO_REJ,
++sp->pp_seq[IDX_LCP], m->m_pkthdr.len + 2,
&h->protocol);
if_inc_counter(ifp, IFCOUNTER_NOPROTO, 1);
goto drop;
case PPP_LCP:
sppp_cp_input(&lcp, sp, m);
m_freem (m);
SPPP_UNLOCK(sp);
return;
case PPP_PAP:
if (sp->pp_phase >= PHASE_AUTHENTICATE)
sppp_pap_input(sp, m);
m_freem (m);
SPPP_UNLOCK(sp);
return;
case PPP_CHAP:
if (sp->pp_phase >= PHASE_AUTHENTICATE)
sppp_chap_input(sp, m);
m_freem (m);
SPPP_UNLOCK(sp);
return;
#ifdef INET
case PPP_IPCP:
if (sp->pp_phase == PHASE_NETWORK)
sppp_cp_input(&ipcp, sp, m);
m_freem (m);
SPPP_UNLOCK(sp);
return;
case PPP_IP:
if (sp->state[IDX_IPCP] == STATE_OPENED) {
isr = NETISR_IP;
}
do_account++;
break;
case PPP_VJ_COMP:
if (sp->state[IDX_IPCP] == STATE_OPENED) {
if ((vjlen =
sl_uncompress_tcp_core(mtod(m, u_char *),
m->m_len, m->m_len,
TYPE_COMPRESSED_TCP,
sp->pp_comp,
&iphdr, &hlen)) <= 0) {
if (debug)
log(LOG_INFO,
SPP_FMT "VJ uncompress failed on compressed packet\n",
SPP_ARGS(ifp));
goto drop;
}
/*
* Trim the VJ header off the packet, and prepend
* the uncompressed IP header (which will usually
* end up in two chained mbufs since there's not
* enough leading space in the existing mbuf).
*/
m_adj(m, vjlen);
M_PREPEND(m, hlen, M_NOWAIT);
if (m == NULL) {
SPPP_UNLOCK(sp);
goto drop2;
}
bcopy(iphdr, mtod(m, u_char *), hlen);
isr = NETISR_IP;
}
do_account++;
break;
case PPP_VJ_UCOMP:
if (sp->state[IDX_IPCP] == STATE_OPENED) {
if (sl_uncompress_tcp_core(mtod(m, u_char *),
m->m_len, m->m_len,
TYPE_UNCOMPRESSED_TCP,
sp->pp_comp,
&iphdr, &hlen) != 0) {
if (debug)
log(LOG_INFO,
SPP_FMT "VJ uncompress failed on uncompressed packet\n",
SPP_ARGS(ifp));
goto drop;
}
isr = NETISR_IP;
}
do_account++;
break;
#endif
#ifdef INET6
case PPP_IPV6CP:
if (sp->pp_phase == PHASE_NETWORK)
sppp_cp_input(&ipv6cp, sp, m);
m_freem (m);
SPPP_UNLOCK(sp);
return;
case PPP_IPV6:
if (sp->state[IDX_IPV6CP] == STATE_OPENED)
isr = NETISR_IPV6;
do_account++;
break;
#endif
}
break;
case CISCO_MULTICAST:
case CISCO_UNICAST:
/* Don't check the control field here (RFC 1547). */
if (sp->pp_mode != IFF_CISCO) {
if (debug)
log(LOG_DEBUG,
SPP_FMT "Cisco packet in PPP mode "
"<addr=0x%x ctrl=0x%x proto=0x%x>\n",
SPP_ARGS(ifp),
h->address, h->control, ntohs(h->protocol));
goto drop;
}
switch (ntohs (h->protocol)) {
default:
if_inc_counter(ifp, IFCOUNTER_NOPROTO, 1);
goto invalid;
case CISCO_KEEPALIVE:
sppp_cisco_input (sp, m);
m_freem (m);
SPPP_UNLOCK(sp);
return;
#ifdef INET
case ETHERTYPE_IP:
isr = NETISR_IP;
do_account++;
break;
#endif
#ifdef INET6
case ETHERTYPE_IPV6:
isr = NETISR_IPV6;
do_account++;
break;
#endif
}
break;
default: /* Invalid PPP packet. */
invalid:
if (debug)
log(LOG_DEBUG,
SPP_FMT "invalid input packet "
"<addr=0x%x ctrl=0x%x proto=0x%x>\n",
SPP_ARGS(ifp),
h->address, h->control, ntohs(h->protocol));
goto drop;
}
if (! (ifp->if_flags & IFF_UP) || isr == -1)
goto drop;
SPPP_UNLOCK(sp);
M_SETFIB(m, ifp->if_fib);
/* Check queue. */
if (netisr_queue(isr, m)) { /* (0) on success. */
if (debug)
log(LOG_DEBUG, SPP_FMT "protocol queue overflow\n",
SPP_ARGS(ifp));
goto drop2;
}
if (do_account)
/*
* Do only account for network packets, not for control
* packets. This is used by some subsystems to detect
* idle lines.
*/
sp->pp_last_recv = time_uptime;
}
static void
sppp_ifstart_sched(void *dummy)
{
struct sppp *sp = dummy;
sp->if_start(SP2IFP(sp));
}
/* if_start () wrapper function. We use it to schedule real if_start () for
* execution. We can't call it directly
*/
static void
sppp_ifstart(struct ifnet *ifp)
{
struct sppp *sp = IFP2SP(ifp);
if (SPPP_LOCK_OWNED(sp)) {
if (callout_pending(&sp->ifstart_callout))
return;
callout_reset(&sp->ifstart_callout, 1, sppp_ifstart_sched,
(void *)sp);
} else {
sp->if_start(ifp);
}
}
/*
* Enqueue transmit packet.
*/
static int
sppp_output(struct ifnet *ifp, struct mbuf *m, const struct sockaddr *dst,
struct route *ro)
{
struct sppp *sp = IFP2SP(ifp);
struct ppp_header *h;
struct ifqueue *ifq = NULL;
int error, rv = 0;
#ifdef INET
int ipproto = PPP_IP;
#endif
int debug = ifp->if_flags & IFF_DEBUG;
SPPP_LOCK(sp);
if (!(ifp->if_flags & IFF_UP) ||
(!(ifp->if_flags & IFF_AUTO) &&
!(ifp->if_drv_flags & IFF_DRV_RUNNING))) {
#ifdef INET6
drop:
#endif
m_freem (m);
SPPP_UNLOCK(sp);
return (ENETDOWN);
}
if ((ifp->if_flags & IFF_AUTO) &&
!(ifp->if_drv_flags & IFF_DRV_RUNNING)) {
#ifdef INET6
/*
* XXX
*
* Hack to prevent the initialization-time generated
* IPv6 multicast packet to erroneously cause a
* dialout event in case IPv6 has been
* administratively disabled on that interface.
*/
if (dst->sa_family == AF_INET6 &&
!(sp->confflags & CONF_ENABLE_IPV6))
goto drop;
#endif
/*
* Interface is not yet running, but auto-dial. Need
* to start LCP for it.
*/
ifp->if_drv_flags |= IFF_DRV_RUNNING;
lcp.Open(sp);
}
#ifdef INET
if (dst->sa_family == AF_INET) {
/* XXX Check mbuf length here? */
struct ip *ip = mtod (m, struct ip*);
struct tcphdr *tcp = (struct tcphdr*) ((long*)ip + ip->ip_hl);
/*
* When using dynamic local IP address assignment by using
* 0.0.0.0 as a local address, the first TCP session will
* not connect because the local TCP checksum is computed
* using 0.0.0.0 which will later become our real IP address
* so the TCP checksum computed at the remote end will
* become invalid. So we
* - don't let packets with src ip addr 0 thru
* - we flag TCP packets with src ip 0 as an error
*/
if(ip->ip_src.s_addr == INADDR_ANY) /* -hm */
{
m_freem(m);
SPPP_UNLOCK(sp);
if(ip->ip_p == IPPROTO_TCP)
return(EADDRNOTAVAIL);
else
return(0);
}
/*
* Put low delay, telnet, rlogin and ftp control packets
* in front of the queue or let ALTQ take care.
*/
if (ALTQ_IS_ENABLED(&ifp->if_snd))
;
else if (_IF_QFULL(&sp->pp_fastq))
;
else if (ip->ip_tos & IPTOS_LOWDELAY)
ifq = &sp->pp_fastq;
else if (m->m_len < sizeof *ip + sizeof *tcp)
;
else if (ip->ip_p != IPPROTO_TCP)
;
else if (INTERACTIVE (ntohs (tcp->th_sport)))
ifq = &sp->pp_fastq;
else if (INTERACTIVE (ntohs (tcp->th_dport)))
ifq = &sp->pp_fastq;
/*
* Do IP Header compression
*/
if (sp->pp_mode != IFF_CISCO && sp->pp_mode != PP_FR &&
(sp->ipcp.flags & IPCP_VJ) && ip->ip_p == IPPROTO_TCP)
switch (sl_compress_tcp(m, ip, sp->pp_comp,
sp->ipcp.compress_cid)) {
case TYPE_COMPRESSED_TCP:
ipproto = PPP_VJ_COMP;
break;
case TYPE_UNCOMPRESSED_TCP:
ipproto = PPP_VJ_UCOMP;
break;
case TYPE_IP:
ipproto = PPP_IP;
break;
default:
m_freem(m);
SPPP_UNLOCK(sp);
return (EINVAL);
}
}
#endif
#ifdef INET6
if (dst->sa_family == AF_INET6) {
/* XXX do something tricky here? */
}
#endif
if (sp->pp_mode == PP_FR) {
/* Add frame relay header. */
m = sppp_fr_header (sp, m, dst->sa_family);
if (! m)
goto nobufs;
goto out;
}
/*
* Prepend general data packet PPP header. For now, IP only.
*/
M_PREPEND (m, PPP_HEADER_LEN, M_NOWAIT);
if (! m) {
nobufs: if (debug)
log(LOG_DEBUG, SPP_FMT "no memory for transmit header\n",
SPP_ARGS(ifp));
if_inc_counter(ifp, IFCOUNTER_OERRORS, 1);
SPPP_UNLOCK(sp);
return (ENOBUFS);
}
/*
* May want to check size of packet
* (albeit due to the implementation it's always enough)
*/
h = mtod (m, struct ppp_header*);
if (sp->pp_mode == IFF_CISCO) {
h->address = CISCO_UNICAST; /* unicast address */
h->control = 0;
} else {
h->address = PPP_ALLSTATIONS; /* broadcast address */
h->control = PPP_UI; /* Unnumbered Info */
}
switch (dst->sa_family) {
#ifdef INET
case AF_INET: /* Internet Protocol */
if (sp->pp_mode == IFF_CISCO)
h->protocol = htons (ETHERTYPE_IP);
else {
/*
* Don't choke with an ENETDOWN early. It's
* possible that we just started dialing out,
* so don't drop the packet immediately. If
* we notice that we run out of buffer space
* below, we will however remember that we are
* not ready to carry IP packets, and return
* ENETDOWN, as opposed to ENOBUFS.
*/
h->protocol = htons(ipproto);
if (sp->state[IDX_IPCP] != STATE_OPENED)
rv = ENETDOWN;
}
break;
#endif
#ifdef INET6
case AF_INET6: /* Internet Protocol */
if (sp->pp_mode == IFF_CISCO)
h->protocol = htons (ETHERTYPE_IPV6);
else {
/*
* Don't choke with an ENETDOWN early. It's
* possible that we just started dialing out,
* so don't drop the packet immediately. If
* we notice that we run out of buffer space
* below, we will however remember that we are
* not ready to carry IP packets, and return
* ENETDOWN, as opposed to ENOBUFS.
*/
h->protocol = htons(PPP_IPV6);
if (sp->state[IDX_IPV6CP] != STATE_OPENED)
rv = ENETDOWN;
}
break;
#endif
default:
m_freem (m);
if_inc_counter(ifp, IFCOUNTER_OERRORS, 1);
SPPP_UNLOCK(sp);
return (EAFNOSUPPORT);
}
/*
* Queue message on interface, and start output if interface
* not yet active.
*/
out:
if (ifq != NULL)
error = !(IF_HANDOFF_ADJ(ifq, m, ifp, 3));
else
IFQ_HANDOFF_ADJ(ifp, m, 3, error);
if (error) {
if_inc_counter(ifp, IFCOUNTER_OERRORS, 1);
SPPP_UNLOCK(sp);
return (rv? rv: ENOBUFS);
}
SPPP_UNLOCK(sp);
/*
* Unlike in sppp_input(), we can always bump the timestamp
* here since sppp_output() is only called on behalf of
* network-layer traffic; control-layer traffic is handled
* by sppp_cp_send().
*/
sp->pp_last_sent = time_uptime;
return (0);
}
void
sppp_attach(struct ifnet *ifp)
{
struct sppp *sp = IFP2SP(ifp);
/* Initialize mtx lock */
mtx_init(&sp->mtx, "sppp", MTX_NETWORK_LOCK, MTX_DEF | MTX_RECURSE);
/* Initialize keepalive handler. */
callout_init(&sp->keepalive_callout, 1);
callout_reset(&sp->keepalive_callout, hz * 10, sppp_keepalive,
(void *)sp);
ifp->if_mtu = PP_MTU;
ifp->if_flags = IFF_POINTOPOINT | IFF_MULTICAST;
ifp->if_output = sppp_output;
#if 0
sp->pp_flags = PP_KEEPALIVE;
#endif
ifp->if_snd.ifq_maxlen = 32;
sp->pp_fastq.ifq_maxlen = 32;
sp->pp_cpq.ifq_maxlen = 20;
sp->pp_loopcnt = 0;
sp->pp_alivecnt = 0;
bzero(&sp->pp_seq[0], sizeof(sp->pp_seq));
bzero(&sp->pp_rseq[0], sizeof(sp->pp_rseq));
sp->pp_phase = PHASE_DEAD;
sp->pp_up = sppp_pp_up;
sp->pp_down = sppp_pp_down;
if(!mtx_initialized(&sp->pp_cpq.ifq_mtx))
mtx_init(&sp->pp_cpq.ifq_mtx, "sppp_cpq", NULL, MTX_DEF);
if(!mtx_initialized(&sp->pp_fastq.ifq_mtx))
mtx_init(&sp->pp_fastq.ifq_mtx, "sppp_fastq", NULL, MTX_DEF);
sp->pp_last_recv = sp->pp_last_sent = time_uptime;
sp->confflags = 0;
#ifdef INET
sp->confflags |= CONF_ENABLE_VJ;
#endif
#ifdef INET6
sp->confflags |= CONF_ENABLE_IPV6;
#endif
callout_init(&sp->ifstart_callout, 1);
sp->if_start = ifp->if_start;
ifp->if_start = sppp_ifstart;
sp->pp_comp = malloc(sizeof(struct slcompress), M_TEMP, M_WAITOK);
sl_compress_init(sp->pp_comp, -1);
sppp_lcp_init(sp);
sppp_ipcp_init(sp);
sppp_ipv6cp_init(sp);
sppp_pap_init(sp);
sppp_chap_init(sp);
}
void
sppp_detach(struct ifnet *ifp)
{
struct sppp *sp = IFP2SP(ifp);
int i;
KASSERT(mtx_initialized(&sp->mtx), ("sppp mutex is not initialized"));
/* Stop keepalive handler. */
callout_drain(&sp->keepalive_callout);
for (i = 0; i < IDX_COUNT; i++) {
callout_drain(&sp->ch[i]);
}
callout_drain(&sp->pap_my_to_ch);
mtx_destroy(&sp->pp_cpq.ifq_mtx);
mtx_destroy(&sp->pp_fastq.ifq_mtx);
mtx_destroy(&sp->mtx);
}
/*
* Flush the interface output queue.
*/
static void
sppp_flush_unlocked(struct ifnet *ifp)
{
struct sppp *sp = IFP2SP(ifp);
sppp_qflush ((struct ifqueue *)&SP2IFP(sp)->if_snd);
sppp_qflush (&sp->pp_fastq);
sppp_qflush (&sp->pp_cpq);
}
void
sppp_flush(struct ifnet *ifp)
{
struct sppp *sp = IFP2SP(ifp);
SPPP_LOCK(sp);
sppp_flush_unlocked (ifp);
SPPP_UNLOCK(sp);
}
/*
* Check if the output queue is empty.
*/
int
sppp_isempty(struct ifnet *ifp)
{
struct sppp *sp = IFP2SP(ifp);
int empty;
SPPP_LOCK(sp);
empty = !sp->pp_fastq.ifq_head && !sp->pp_cpq.ifq_head &&
!SP2IFP(sp)->if_snd.ifq_head;
SPPP_UNLOCK(sp);
return (empty);
}
/*
* Get next packet to send.
*/
struct mbuf *
sppp_dequeue(struct ifnet *ifp)
{
struct sppp *sp = IFP2SP(ifp);
struct mbuf *m;
SPPP_LOCK(sp);
/*
* Process only the control protocol queue until we have at
* least one NCP open.
*
* Do always serve all three queues in Cisco mode.
*/
IF_DEQUEUE(&sp->pp_cpq, m);
if (m == NULL &&
(sppp_ncp_check(sp) || sp->pp_mode == IFF_CISCO ||
sp->pp_mode == PP_FR)) {
IF_DEQUEUE(&sp->pp_fastq, m);
if (m == NULL)
IF_DEQUEUE (&SP2IFP(sp)->if_snd, m);
}
SPPP_UNLOCK(sp);
return m;
}
/*
* Pick the next packet, do not remove it from the queue.
*/
struct mbuf *
sppp_pick(struct ifnet *ifp)
{
struct sppp *sp = IFP2SP(ifp);
struct mbuf *m;
SPPP_LOCK(sp);
m = sp->pp_cpq.ifq_head;
if (m == NULL &&
(sp->pp_phase == PHASE_NETWORK ||
sp->pp_mode == IFF_CISCO ||
sp->pp_mode == PP_FR))
if ((m = sp->pp_fastq.ifq_head) == NULL)
m = SP2IFP(sp)->if_snd.ifq_head;
SPPP_UNLOCK(sp);
return (m);
}
/*
* Process an ioctl request. Called on low priority level.
*/
int
sppp_ioctl(struct ifnet *ifp, IOCTL_CMD_T cmd, void *data)
{
struct ifreq *ifr = (struct ifreq*) data;
struct sppp *sp = IFP2SP(ifp);
int rv, going_up, going_down, newmode;
SPPP_LOCK(sp);
rv = 0;
switch (cmd) {
case SIOCAIFADDR:
break;
case SIOCSIFADDR:
/* set the interface "up" when assigning an IP address */
ifp->if_flags |= IFF_UP;
/* FALLTHROUGH */
case SIOCSIFFLAGS:
going_up = ifp->if_flags & IFF_UP &&
(ifp->if_drv_flags & IFF_DRV_RUNNING) == 0;
going_down = (ifp->if_flags & IFF_UP) == 0 &&
ifp->if_drv_flags & IFF_DRV_RUNNING;
newmode = ifp->if_flags & IFF_PASSIVE;
if (!newmode)
newmode = ifp->if_flags & IFF_AUTO;
if (!newmode)
newmode = ifp->if_flags & IFF_CISCO;
ifp->if_flags &= ~(IFF_PASSIVE | IFF_AUTO | IFF_CISCO);
ifp->if_flags |= newmode;
if (!newmode)
newmode = sp->pp_flags & PP_FR;
if (newmode != sp->pp_mode) {
going_down = 1;
if (!going_up)
going_up = ifp->if_drv_flags & IFF_DRV_RUNNING;
}
if (going_down) {
if (sp->pp_mode != IFF_CISCO &&
sp->pp_mode != PP_FR)
lcp.Close(sp);
else if (sp->pp_tlf)
(sp->pp_tlf)(sp);
sppp_flush_unlocked(ifp);
ifp->if_drv_flags &= ~IFF_DRV_RUNNING;
sp->pp_mode = newmode;
}
if (going_up) {
if (sp->pp_mode != IFF_CISCO &&
sp->pp_mode != PP_FR)
lcp.Close(sp);
sp->pp_mode = newmode;
if (sp->pp_mode == 0) {
ifp->if_drv_flags |= IFF_DRV_RUNNING;
lcp.Open(sp);
}
if ((sp->pp_mode == IFF_CISCO) ||
(sp->pp_mode == PP_FR)) {
if (sp->pp_tls)
(sp->pp_tls)(sp);
ifp->if_drv_flags |= IFF_DRV_RUNNING;
}
}
break;
#ifdef SIOCSIFMTU
#ifndef ifr_mtu
#define ifr_mtu ifr_metric
#endif
case SIOCSIFMTU:
if (ifr->ifr_mtu < 128 || ifr->ifr_mtu > sp->lcp.their_mru)
return (EINVAL);
ifp->if_mtu = ifr->ifr_mtu;
break;
#endif
#ifdef SLIOCSETMTU
case SLIOCSETMTU:
if (*(short*)data < 128 || *(short*)data > sp->lcp.their_mru)
return (EINVAL);
ifp->if_mtu = *(short*)data;
break;
#endif
#ifdef SIOCGIFMTU
case SIOCGIFMTU:
ifr->ifr_mtu = ifp->if_mtu;
break;
#endif
#ifdef SLIOCGETMTU
case SLIOCGETMTU:
*(short*)data = ifp->if_mtu;
break;
#endif
case SIOCADDMULTI:
case SIOCDELMULTI:
break;
case SIOCGIFGENERIC:
case SIOCSIFGENERIC:
rv = sppp_params(sp, cmd, data);
break;
default:
rv = ENOTTY;
}
SPPP_UNLOCK(sp);
return rv;
}
/*
* Cisco framing implementation.
*/
/*
* Handle incoming Cisco keepalive protocol packets.
*/
static void
sppp_cisco_input(struct sppp *sp, struct mbuf *m)
{
STDDCL;
struct cisco_packet *h;
u_long me, mymask;
if (m->m_pkthdr.len < CISCO_PACKET_LEN) {
if (debug)
log(LOG_DEBUG,
SPP_FMT "cisco invalid packet length: %d bytes\n",
SPP_ARGS(ifp), m->m_pkthdr.len);
return;
}
h = mtod (m, struct cisco_packet*);
if (debug)
log(LOG_DEBUG,
SPP_FMT "cisco input: %d bytes "
"<0x%lx 0x%lx 0x%lx 0x%x 0x%x-0x%x>\n",
SPP_ARGS(ifp), m->m_pkthdr.len,
(u_long)ntohl (h->type), (u_long)h->par1, (u_long)h->par2, (u_int)h->rel,
(u_int)h->time0, (u_int)h->time1);
switch (ntohl (h->type)) {
default:
if (debug)
log(-1, SPP_FMT "cisco unknown packet type: 0x%lx\n",
SPP_ARGS(ifp), (u_long)ntohl (h->type));
break;
case CISCO_ADDR_REPLY:
/* Reply on address request, ignore */
break;
case CISCO_KEEPALIVE_REQ:
sp->pp_alivecnt = 0;
sp->pp_rseq[IDX_LCP] = ntohl (h->par1);
if (sp->pp_seq[IDX_LCP] == sp->pp_rseq[IDX_LCP]) {
/* Local and remote sequence numbers are equal.
* Probably, the line is in loopback mode. */
if (sp->pp_loopcnt >= MAXALIVECNT) {
printf (SPP_FMT "loopback\n",
SPP_ARGS(ifp));
sp->pp_loopcnt = 0;
if (ifp->if_flags & IFF_UP) {
if_down (ifp);
sppp_qflush (&sp->pp_cpq);
}
}
++sp->pp_loopcnt;
/* Generate new local sequence number */
sp->pp_seq[IDX_LCP] = random();
break;
}
sp->pp_loopcnt = 0;
if (! (ifp->if_flags & IFF_UP) &&
(ifp->if_drv_flags & IFF_DRV_RUNNING)) {
if_up(ifp);
printf (SPP_FMT "up\n", SPP_ARGS(ifp));
}
break;
case CISCO_ADDR_REQ:
sppp_get_ip_addrs(sp, &me, 0, &mymask);
if (me != 0L)
sppp_cisco_send(sp, CISCO_ADDR_REPLY, me, mymask);
break;
}
}
/*
* Send Cisco keepalive packet.
*/
static void
sppp_cisco_send(struct sppp *sp, int type, long par1, long par2)
{
STDDCL;
struct ppp_header *h;
struct cisco_packet *ch;
struct mbuf *m;
struct timeval tv;
getmicrouptime(&tv);
MGETHDR (m, M_NOWAIT, MT_DATA);
if (! m)
return;
m->m_pkthdr.len = m->m_len = PPP_HEADER_LEN + CISCO_PACKET_LEN;
m->m_pkthdr.rcvif = 0;
h = mtod (m, struct ppp_header*);
h->address = CISCO_MULTICAST;
h->control = 0;
h->protocol = htons (CISCO_KEEPALIVE);
ch = (struct cisco_packet*) (h + 1);
ch->type = htonl (type);
ch->par1 = htonl (par1);
ch->par2 = htonl (par2);
ch->rel = -1;
ch->time0 = htons ((u_short) (tv.tv_sec >> 16));
ch->time1 = htons ((u_short) tv.tv_sec);
if (debug)
log(LOG_DEBUG,
SPP_FMT "cisco output: <0x%lx 0x%lx 0x%lx 0x%x 0x%x-0x%x>\n",
SPP_ARGS(ifp), (u_long)ntohl (ch->type), (u_long)ch->par1,
(u_long)ch->par2, (u_int)ch->rel, (u_int)ch->time0, (u_int)ch->time1);
if (! IF_HANDOFF_ADJ(&sp->pp_cpq, m, ifp, 3))
if_inc_counter(ifp, IFCOUNTER_OERRORS, 1);
}
/*
* PPP protocol implementation.
*/
/*
* Send PPP control protocol packet.
*/
static void
sppp_cp_send(struct sppp *sp, u_short proto, u_char type,
u_char ident, u_short len, void *data)
{
STDDCL;
struct ppp_header *h;
struct lcp_header *lh;
struct mbuf *m;
if (len > MHLEN - PPP_HEADER_LEN - LCP_HEADER_LEN)
len = MHLEN - PPP_HEADER_LEN - LCP_HEADER_LEN;
MGETHDR (m, M_NOWAIT, MT_DATA);
if (! m)
return;
m->m_pkthdr.len = m->m_len = PPP_HEADER_LEN + LCP_HEADER_LEN + len;
m->m_pkthdr.rcvif = 0;
h = mtod (m, struct ppp_header*);
h->address = PPP_ALLSTATIONS; /* broadcast address */
h->control = PPP_UI; /* Unnumbered Info */
h->protocol = htons (proto); /* Link Control Protocol */
lh = (struct lcp_header*) (h + 1);
lh->type = type;
lh->ident = ident;
lh->len = htons (LCP_HEADER_LEN + len);
if (len)
bcopy (data, lh+1, len);
if (debug) {
log(LOG_DEBUG, SPP_FMT "%s output <%s id=0x%x len=%d",
SPP_ARGS(ifp),
sppp_proto_name(proto),
sppp_cp_type_name (lh->type), lh->ident,
ntohs (lh->len));
sppp_print_bytes ((u_char*) (lh+1), len);
log(-1, ">\n");
}
if (! IF_HANDOFF_ADJ(&sp->pp_cpq, m, ifp, 3))
if_inc_counter(ifp, IFCOUNTER_OERRORS, 1);
}
/*
* Handle incoming PPP control protocol packets.
*/
static void
sppp_cp_input(const struct cp *cp, struct sppp *sp, struct mbuf *m)
{
STDDCL;
struct lcp_header *h;
int len = m->m_pkthdr.len;
int rv;
u_char *p;
if (len < 4) {
if (debug)
log(LOG_DEBUG,
SPP_FMT "%s invalid packet length: %d bytes\n",
SPP_ARGS(ifp), cp->name, len);
return;
}
h = mtod (m, struct lcp_header*);
if (debug) {
log(LOG_DEBUG,
SPP_FMT "%s input(%s): <%s id=0x%x len=%d",
SPP_ARGS(ifp), cp->name,
sppp_state_name(sp->state[cp->protoidx]),
sppp_cp_type_name (h->type), h->ident, ntohs (h->len));
sppp_print_bytes ((u_char*) (h+1), len-4);
log(-1, ">\n");
}
if (len > ntohs (h->len))
len = ntohs (h->len);
p = (u_char *)(h + 1);
switch (h->type) {
case CONF_REQ:
if (len < 4) {
if (debug)
log(-1, SPP_FMT "%s invalid conf-req length %d\n",
SPP_ARGS(ifp), cp->name,
len);
if_inc_counter(ifp, IFCOUNTER_IERRORS, 1);
break;
}
/* handle states where RCR doesn't get a SCA/SCN */
switch (sp->state[cp->protoidx]) {
case STATE_CLOSING:
case STATE_STOPPING:
return;
case STATE_CLOSED:
sppp_cp_send(sp, cp->proto, TERM_ACK, h->ident,
0, 0);
return;
}
rv = (cp->RCR)(sp, h, len);
switch (sp->state[cp->protoidx]) {
case STATE_OPENED:
(cp->tld)(sp);
(cp->scr)(sp);
/* FALLTHROUGH */
case STATE_ACK_SENT:
case STATE_REQ_SENT:
/*
* sppp_cp_change_state() have the side effect of
* restarting the timeouts. We want to avoid that
* if the state don't change, otherwise we won't
* ever timeout and resend a configuration request
* that got lost.
*/
if (sp->state[cp->protoidx] == (rv ? STATE_ACK_SENT:
STATE_REQ_SENT))
break;
sppp_cp_change_state(cp, sp, rv?
STATE_ACK_SENT: STATE_REQ_SENT);
break;
case STATE_STOPPED:
sp->rst_counter[cp->protoidx] = sp->lcp.max_configure;
(cp->scr)(sp);
sppp_cp_change_state(cp, sp, rv?
STATE_ACK_SENT: STATE_REQ_SENT);
break;
case STATE_ACK_RCVD:
if (rv) {
sppp_cp_change_state(cp, sp, STATE_OPENED);
if (debug)
log(LOG_DEBUG, SPP_FMT "%s tlu\n",
SPP_ARGS(ifp),
cp->name);
(cp->tlu)(sp);
} else
sppp_cp_change_state(cp, sp, STATE_ACK_RCVD);
break;
default:
printf(SPP_FMT "%s illegal %s in state %s\n",
SPP_ARGS(ifp), cp->name,
sppp_cp_type_name(h->type),
sppp_state_name(sp->state[cp->protoidx]));
if_inc_counter(ifp, IFCOUNTER_IERRORS, 1);
}
break;
case CONF_ACK:
if (h->ident != sp->confid[cp->protoidx]) {
if (debug)
log(-1, SPP_FMT "%s id mismatch 0x%x != 0x%x\n",
SPP_ARGS(ifp), cp->name,
h->ident, sp->confid[cp->protoidx]);
if_inc_counter(ifp, IFCOUNTER_IERRORS, 1);
break;
}
switch (sp->state[cp->protoidx]) {
case STATE_CLOSED:
case STATE_STOPPED:
sppp_cp_send(sp, cp->proto, TERM_ACK, h->ident, 0, 0);
break;
case STATE_CLOSING:
case STATE_STOPPING:
break;
case STATE_REQ_SENT:
sp->rst_counter[cp->protoidx] = sp->lcp.max_configure;
sppp_cp_change_state(cp, sp, STATE_ACK_RCVD);
break;
case STATE_OPENED:
(cp->tld)(sp);
/* FALLTHROUGH */
case STATE_ACK_RCVD:
(cp->scr)(sp);
sppp_cp_change_state(cp, sp, STATE_REQ_SENT);
break;
case STATE_ACK_SENT:
sp->rst_counter[cp->protoidx] = sp->lcp.max_configure;
sppp_cp_change_state(cp, sp, STATE_OPENED);
if (debug)
log(LOG_DEBUG, SPP_FMT "%s tlu\n",
SPP_ARGS(ifp), cp->name);
(cp->tlu)(sp);
break;
default:
printf(SPP_FMT "%s illegal %s in state %s\n",
SPP_ARGS(ifp), cp->name,
sppp_cp_type_name(h->type),
sppp_state_name(sp->state[cp->protoidx]));
if_inc_counter(ifp, IFCOUNTER_IERRORS, 1);
}
break;
case CONF_NAK:
case CONF_REJ:
if (h->ident != sp->confid[cp->protoidx]) {
if (debug)
log(-1, SPP_FMT "%s id mismatch 0x%x != 0x%x\n",
SPP_ARGS(ifp), cp->name,
h->ident, sp->confid[cp->protoidx]);
if_inc_counter(ifp, IFCOUNTER_IERRORS, 1);
break;
}
if (h->type == CONF_NAK)
(cp->RCN_nak)(sp, h, len);
else /* CONF_REJ */
(cp->RCN_rej)(sp, h, len);
switch (sp->state[cp->protoidx]) {
case STATE_CLOSED:
case STATE_STOPPED:
sppp_cp_send(sp, cp->proto, TERM_ACK, h->ident, 0, 0);
break;
case STATE_REQ_SENT:
case STATE_ACK_SENT:
sp->rst_counter[cp->protoidx] = sp->lcp.max_configure;
/*
* Slow things down a bit if we think we might be
* in loopback. Depend on the timeout to send the
* next configuration request.
*/
if (sp->pp_loopcnt)
break;
(cp->scr)(sp);
break;
case STATE_OPENED:
(cp->tld)(sp);
/* FALLTHROUGH */
case STATE_ACK_RCVD:
sppp_cp_change_state(cp, sp, STATE_REQ_SENT);
(cp->scr)(sp);
break;
case STATE_CLOSING:
case STATE_STOPPING:
break;
default:
printf(SPP_FMT "%s illegal %s in state %s\n",
SPP_ARGS(ifp), cp->name,
sppp_cp_type_name(h->type),
sppp_state_name(sp->state[cp->protoidx]));
if_inc_counter(ifp, IFCOUNTER_IERRORS, 1);
}
break;
case TERM_REQ:
switch (sp->state[cp->protoidx]) {
case STATE_ACK_RCVD:
case STATE_ACK_SENT:
sppp_cp_change_state(cp, sp, STATE_REQ_SENT);
/* FALLTHROUGH */
case STATE_CLOSED:
case STATE_STOPPED:
case STATE_CLOSING:
case STATE_STOPPING:
case STATE_REQ_SENT:
sta:
/* Send Terminate-Ack packet. */
if (debug)
log(LOG_DEBUG, SPP_FMT "%s send terminate-ack\n",
SPP_ARGS(ifp), cp->name);
sppp_cp_send(sp, cp->proto, TERM_ACK, h->ident, 0, 0);
break;
case STATE_OPENED:
(cp->tld)(sp);
sp->rst_counter[cp->protoidx] = 0;
sppp_cp_change_state(cp, sp, STATE_STOPPING);
goto sta;
break;
default:
printf(SPP_FMT "%s illegal %s in state %s\n",
SPP_ARGS(ifp), cp->name,
sppp_cp_type_name(h->type),
sppp_state_name(sp->state[cp->protoidx]));
if_inc_counter(ifp, IFCOUNTER_IERRORS, 1);
}
break;
case TERM_ACK:
switch (sp->state[cp->protoidx]) {
case STATE_CLOSED:
case STATE_STOPPED:
case STATE_REQ_SENT:
case STATE_ACK_SENT:
break;
case STATE_CLOSING:
sppp_cp_change_state(cp, sp, STATE_CLOSED);
(cp->tlf)(sp);
break;
case STATE_STOPPING:
sppp_cp_change_state(cp, sp, STATE_STOPPED);
(cp->tlf)(sp);
break;
case STATE_ACK_RCVD:
sppp_cp_change_state(cp, sp, STATE_REQ_SENT);
break;
case STATE_OPENED:
(cp->tld)(sp);
(cp->scr)(sp);
sppp_cp_change_state(cp, sp, STATE_ACK_RCVD);
break;
default:
printf(SPP_FMT "%s illegal %s in state %s\n",
SPP_ARGS(ifp), cp->name,
sppp_cp_type_name(h->type),
sppp_state_name(sp->state[cp->protoidx]));
if_inc_counter(ifp, IFCOUNTER_IERRORS, 1);
}
break;
case CODE_REJ:
/* XXX catastrophic rejects (RXJ-) aren't handled yet. */
log(LOG_INFO,
SPP_FMT "%s: ignoring RXJ (%s) for proto 0x%x, "
"danger will robinson\n",
SPP_ARGS(ifp), cp->name,
sppp_cp_type_name(h->type), ntohs(*((u_short *)p)));
switch (sp->state[cp->protoidx]) {
case STATE_CLOSED:
case STATE_STOPPED:
case STATE_REQ_SENT:
case STATE_ACK_SENT:
case STATE_CLOSING:
case STATE_STOPPING:
case STATE_OPENED:
break;
case STATE_ACK_RCVD:
sppp_cp_change_state(cp, sp, STATE_REQ_SENT);
break;
default:
printf(SPP_FMT "%s illegal %s in state %s\n",
SPP_ARGS(ifp), cp->name,
sppp_cp_type_name(h->type),
sppp_state_name(sp->state[cp->protoidx]));
if_inc_counter(ifp, IFCOUNTER_IERRORS, 1);
}
break;
case PROTO_REJ:
{
int catastrophic;
const struct cp *upper;
int i;
u_int16_t proto;
catastrophic = 0;
upper = NULL;
proto = ntohs(*((u_int16_t *)p));
for (i = 0; i < IDX_COUNT; i++) {
if (cps[i]->proto == proto) {
upper = cps[i];
break;
}
}
if (upper == NULL)
catastrophic++;
if (catastrophic || debug)
log(catastrophic? LOG_INFO: LOG_DEBUG,
SPP_FMT "%s: RXJ%c (%s) for proto 0x%x (%s/%s)\n",
SPP_ARGS(ifp), cp->name, catastrophic ? '-' : '+',
sppp_cp_type_name(h->type), proto,
upper ? upper->name : "unknown",
upper ? sppp_state_name(sp->state[upper->protoidx]) : "?");
/*
* if we got RXJ+ against conf-req, the peer does not implement
* this particular protocol type. terminate the protocol.
*/
if (upper && !catastrophic) {
if (sp->state[upper->protoidx] == STATE_REQ_SENT) {
upper->Close(sp);
break;
}
}
/* XXX catastrophic rejects (RXJ-) aren't handled yet. */
switch (sp->state[cp->protoidx]) {
case STATE_CLOSED:
case STATE_STOPPED:
case STATE_REQ_SENT:
case STATE_ACK_SENT:
case STATE_CLOSING:
case STATE_STOPPING:
case STATE_OPENED:
break;
case STATE_ACK_RCVD:
sppp_cp_change_state(cp, sp, STATE_REQ_SENT);
break;
default:
printf(SPP_FMT "%s illegal %s in state %s\n",
SPP_ARGS(ifp), cp->name,
sppp_cp_type_name(h->type),
sppp_state_name(sp->state[cp->protoidx]));
if_inc_counter(ifp, IFCOUNTER_IERRORS, 1);
}
break;
}
case DISC_REQ:
if (cp->proto != PPP_LCP)
goto illegal;
/* Discard the packet. */
break;
case ECHO_REQ:
if (cp->proto != PPP_LCP)
goto illegal;
if (sp->state[cp->protoidx] != STATE_OPENED) {
if (debug)
log(-1, SPP_FMT "lcp echo req but lcp closed\n",
SPP_ARGS(ifp));
if_inc_counter(ifp, IFCOUNTER_IERRORS, 1);
break;
}
if (len < 8) {
if (debug)
log(-1, SPP_FMT "invalid lcp echo request "
"packet length: %d bytes\n",
SPP_ARGS(ifp), len);
break;
}
if ((sp->lcp.opts & (1 << LCP_OPT_MAGIC)) &&
ntohl (*(long*)(h+1)) == sp->lcp.magic) {
/* Line loopback mode detected. */
printf(SPP_FMT "loopback\n", SPP_ARGS(ifp));
sp->pp_loopcnt = MAXALIVECNT * 5;
if_down (ifp);
sppp_qflush (&sp->pp_cpq);
/* Shut down the PPP link. */
/* XXX */
lcp.Down(sp);
lcp.Up(sp);
break;
}
*(long*)(h+1) = htonl (sp->lcp.magic);
if (debug)
log(-1, SPP_FMT "got lcp echo req, sending echo rep\n",
SPP_ARGS(ifp));
sppp_cp_send (sp, PPP_LCP, ECHO_REPLY, h->ident, len-4, h+1);
break;
case ECHO_REPLY:
if (cp->proto != PPP_LCP)
goto illegal;
if (h->ident != sp->lcp.echoid) {
if_inc_counter(ifp, IFCOUNTER_IERRORS, 1);
break;
}
if (len < 8) {
if (debug)
log(-1, SPP_FMT "lcp invalid echo reply "
"packet length: %d bytes\n",
SPP_ARGS(ifp), len);
break;
}
if (debug)
log(-1, SPP_FMT "lcp got echo rep\n",
SPP_ARGS(ifp));
if (!(sp->lcp.opts & (1 << LCP_OPT_MAGIC)) ||
ntohl (*(long*)(h+1)) != sp->lcp.magic)
sp->pp_alivecnt = 0;
break;
default:
/* Unknown packet type -- send Code-Reject packet. */
illegal:
if (debug)
log(-1, SPP_FMT "%s send code-rej for 0x%x\n",
SPP_ARGS(ifp), cp->name, h->type);
sppp_cp_send(sp, cp->proto, CODE_REJ,
++sp->pp_seq[cp->protoidx], m->m_pkthdr.len, h);
if_inc_counter(ifp, IFCOUNTER_IERRORS, 1);
}
}
/*
* The generic part of all Up/Down/Open/Close/TO event handlers.
* Basically, the state transition handling in the automaton.
*/
static void
sppp_up_event(const struct cp *cp, struct sppp *sp)
{
STDDCL;
if (debug)
log(LOG_DEBUG, SPP_FMT "%s up(%s)\n",
SPP_ARGS(ifp), cp->name,
sppp_state_name(sp->state[cp->protoidx]));
switch (sp->state[cp->protoidx]) {
case STATE_INITIAL:
sppp_cp_change_state(cp, sp, STATE_CLOSED);
break;
case STATE_STARTING:
sp->rst_counter[cp->protoidx] = sp->lcp.max_configure;
(cp->scr)(sp);
sppp_cp_change_state(cp, sp, STATE_REQ_SENT);
break;
default:
printf(SPP_FMT "%s illegal up in state %s\n",
SPP_ARGS(ifp), cp->name,
sppp_state_name(sp->state[cp->protoidx]));
}
}
static void
sppp_down_event(const struct cp *cp, struct sppp *sp)
{
STDDCL;
if (debug)
log(LOG_DEBUG, SPP_FMT "%s down(%s)\n",
SPP_ARGS(ifp), cp->name,
sppp_state_name(sp->state[cp->protoidx]));
switch (sp->state[cp->protoidx]) {
case STATE_CLOSED:
case STATE_CLOSING:
sppp_cp_change_state(cp, sp, STATE_INITIAL);
break;
case STATE_STOPPED:
sppp_cp_change_state(cp, sp, STATE_STARTING);
(cp->tls)(sp);
break;
case STATE_STOPPING:
case STATE_REQ_SENT:
case STATE_ACK_RCVD:
case STATE_ACK_SENT:
sppp_cp_change_state(cp, sp, STATE_STARTING);
break;
case STATE_OPENED:
(cp->tld)(sp);
sppp_cp_change_state(cp, sp, STATE_STARTING);
break;
default:
printf(SPP_FMT "%s illegal down in state %s\n",
SPP_ARGS(ifp), cp->name,
sppp_state_name(sp->state[cp->protoidx]));
}
}
static void
sppp_open_event(const struct cp *cp, struct sppp *sp)
{
STDDCL;
if (debug)
log(LOG_DEBUG, SPP_FMT "%s open(%s)\n",
SPP_ARGS(ifp), cp->name,
sppp_state_name(sp->state[cp->protoidx]));
switch (sp->state[cp->protoidx]) {
case STATE_INITIAL:
sppp_cp_change_state(cp, sp, STATE_STARTING);
(cp->tls)(sp);
break;
case STATE_STARTING:
break;
case STATE_CLOSED:
sp->rst_counter[cp->protoidx] = sp->lcp.max_configure;
(cp->scr)(sp);
sppp_cp_change_state(cp, sp, STATE_REQ_SENT);
break;
case STATE_STOPPED:
/*
* Try escaping stopped state. This seems to bite
* people occasionally, in particular for IPCP,
* presumably following previous IPCP negotiation
* aborts. Somehow, we must have missed a Down event
* which would have caused a transition into starting
* state, so as a bandaid we force the Down event now.
* This effectively implements (something like the)
* `restart' option mentioned in the state transition
* table of RFC 1661.
*/
sppp_cp_change_state(cp, sp, STATE_STARTING);
(cp->tls)(sp);
break;
case STATE_STOPPING:
case STATE_REQ_SENT:
case STATE_ACK_RCVD:
case STATE_ACK_SENT:
case STATE_OPENED:
break;
case STATE_CLOSING:
sppp_cp_change_state(cp, sp, STATE_STOPPING);
break;
}
}
static void
sppp_close_event(const struct cp *cp, struct sppp *sp)
{
STDDCL;
if (debug)
log(LOG_DEBUG, SPP_FMT "%s close(%s)\n",
SPP_ARGS(ifp), cp->name,
sppp_state_name(sp->state[cp->protoidx]));
switch (sp->state[cp->protoidx]) {
case STATE_INITIAL:
case STATE_CLOSED:
case STATE_CLOSING:
break;
case STATE_STARTING:
sppp_cp_change_state(cp, sp, STATE_INITIAL);
(cp->tlf)(sp);
break;
case STATE_STOPPED:
sppp_cp_change_state(cp, sp, STATE_CLOSED);
break;
case STATE_STOPPING:
sppp_cp_change_state(cp, sp, STATE_CLOSING);
break;
case STATE_OPENED:
(cp->tld)(sp);
/* FALLTHROUGH */
case STATE_REQ_SENT:
case STATE_ACK_RCVD:
case STATE_ACK_SENT:
sp->rst_counter[cp->protoidx] = sp->lcp.max_terminate;
sppp_cp_send(sp, cp->proto, TERM_REQ,
++sp->pp_seq[cp->protoidx], 0, 0);
sppp_cp_change_state(cp, sp, STATE_CLOSING);
break;
}
}
static void
sppp_to_event(const struct cp *cp, struct sppp *sp)
{
STDDCL;
SPPP_LOCK(sp);
if (debug)
log(LOG_DEBUG, SPP_FMT "%s TO(%s) rst_counter = %d\n",
SPP_ARGS(ifp), cp->name,
sppp_state_name(sp->state[cp->protoidx]),
sp->rst_counter[cp->protoidx]);
if (--sp->rst_counter[cp->protoidx] < 0)
/* TO- event */
switch (sp->state[cp->protoidx]) {
case STATE_CLOSING:
sppp_cp_change_state(cp, sp, STATE_CLOSED);
(cp->tlf)(sp);
break;
case STATE_STOPPING:
sppp_cp_change_state(cp, sp, STATE_STOPPED);
(cp->tlf)(sp);
break;
case STATE_REQ_SENT:
case STATE_ACK_RCVD:
case STATE_ACK_SENT:
sppp_cp_change_state(cp, sp, STATE_STOPPED);
(cp->tlf)(sp);
break;
}
else
/* TO+ event */
switch (sp->state[cp->protoidx]) {
case STATE_CLOSING:
case STATE_STOPPING:
sppp_cp_send(sp, cp->proto, TERM_REQ,
++sp->pp_seq[cp->protoidx], 0, 0);
callout_reset(&sp->ch[cp->protoidx], sp->lcp.timeout,
cp->TO, (void *)sp);
break;
case STATE_REQ_SENT:
case STATE_ACK_RCVD:
(cp->scr)(sp);
/* sppp_cp_change_state() will restart the timer */
sppp_cp_change_state(cp, sp, STATE_REQ_SENT);
break;
case STATE_ACK_SENT:
(cp->scr)(sp);
callout_reset(&sp->ch[cp->protoidx], sp->lcp.timeout,
cp->TO, (void *)sp);
break;
}
SPPP_UNLOCK(sp);
}
/*
* Change the state of a control protocol in the state automaton.
* Takes care of starting/stopping the restart timer.
*/
static void
sppp_cp_change_state(const struct cp *cp, struct sppp *sp, int newstate)
{
sp->state[cp->protoidx] = newstate;
callout_stop (&sp->ch[cp->protoidx]);
switch (newstate) {
case STATE_INITIAL:
case STATE_STARTING:
case STATE_CLOSED:
case STATE_STOPPED:
case STATE_OPENED:
break;
case STATE_CLOSING:
case STATE_STOPPING:
case STATE_REQ_SENT:
case STATE_ACK_RCVD:
case STATE_ACK_SENT:
callout_reset(&sp->ch[cp->protoidx], sp->lcp.timeout,
cp->TO, (void *)sp);
break;
}
}
/*
*--------------------------------------------------------------------------*
* *
* The LCP implementation. *
* *
*--------------------------------------------------------------------------*
*/
static void
sppp_pp_up(struct sppp *sp)
{
SPPP_LOCK(sp);
lcp.Up(sp);
SPPP_UNLOCK(sp);
}
static void
sppp_pp_down(struct sppp *sp)
{
SPPP_LOCK(sp);
lcp.Down(sp);
SPPP_UNLOCK(sp);
}
static void
sppp_lcp_init(struct sppp *sp)
{
sp->lcp.opts = (1 << LCP_OPT_MAGIC);
sp->lcp.magic = 0;
sp->state[IDX_LCP] = STATE_INITIAL;
sp->fail_counter[IDX_LCP] = 0;
sp->pp_seq[IDX_LCP] = 0;
sp->pp_rseq[IDX_LCP] = 0;
sp->lcp.protos = 0;
sp->lcp.mru = sp->lcp.their_mru = PP_MTU;
/* Note that these values are relevant for all control protocols */
sp->lcp.timeout = 3 * hz;
sp->lcp.max_terminate = 2;
sp->lcp.max_configure = 10;
sp->lcp.max_failure = 10;
callout_init(&sp->ch[IDX_LCP], 1);
}
static void
sppp_lcp_up(struct sppp *sp)
{
STDDCL;
sp->pp_alivecnt = 0;
sp->lcp.opts = (1 << LCP_OPT_MAGIC);
sp->lcp.magic = 0;
sp->lcp.protos = 0;
sp->lcp.mru = sp->lcp.their_mru = PP_MTU;
/*
* If we are authenticator, negotiate LCP_AUTH
*/
if (sp->hisauth.proto != 0)
sp->lcp.opts |= (1 << LCP_OPT_AUTH_PROTO);
else
sp->lcp.opts &= ~(1 << LCP_OPT_AUTH_PROTO);
sp->pp_flags &= ~PP_NEEDAUTH;
/*
* If this interface is passive or dial-on-demand, and we are
* still in Initial state, it means we've got an incoming
* call. Activate the interface.
*/
if ((ifp->if_flags & (IFF_AUTO | IFF_PASSIVE)) != 0) {
if (debug)
log(LOG_DEBUG,
SPP_FMT "Up event", SPP_ARGS(ifp));
ifp->if_drv_flags |= IFF_DRV_RUNNING;
if (sp->state[IDX_LCP] == STATE_INITIAL) {
if (debug)
log(-1, "(incoming call)\n");
sp->pp_flags |= PP_CALLIN;
lcp.Open(sp);
} else if (debug)
log(-1, "\n");
} else if ((ifp->if_flags & (IFF_AUTO | IFF_PASSIVE)) == 0 &&
(sp->state[IDX_LCP] == STATE_INITIAL)) {
ifp->if_drv_flags |= IFF_DRV_RUNNING;
lcp.Open(sp);
}
sppp_up_event(&lcp, sp);
}
static void
sppp_lcp_down(struct sppp *sp)
{
STDDCL;
sppp_down_event(&lcp, sp);
/*
* If this is neither a dial-on-demand nor a passive
* interface, simulate an ``ifconfig down'' action, so the
* administrator can force a redial by another ``ifconfig
* up''. XXX For leased line operation, should we immediately
* try to reopen the connection here?
*/
if ((ifp->if_flags & (IFF_AUTO | IFF_PASSIVE)) == 0) {
log(LOG_INFO,
SPP_FMT "Down event, taking interface down.\n",
SPP_ARGS(ifp));
if_down(ifp);
} else {
if (debug)
log(LOG_DEBUG,
SPP_FMT "Down event (carrier loss)\n",
SPP_ARGS(ifp));
sp->pp_flags &= ~PP_CALLIN;
if (sp->state[IDX_LCP] != STATE_INITIAL)
lcp.Close(sp);
ifp->if_drv_flags &= ~IFF_DRV_RUNNING;
}
}
static void
sppp_lcp_open(struct sppp *sp)
{
sppp_open_event(&lcp, sp);
}
static void
sppp_lcp_close(struct sppp *sp)
{
sppp_close_event(&lcp, sp);
}
static void
sppp_lcp_TO(void *cookie)
{
sppp_to_event(&lcp, (struct sppp *)cookie);
}
/*
* Analyze a configure request. Return true if it was agreeable, and
* caused action sca, false if it has been rejected or nak'ed, and
* caused action scn. (The return value is used to make the state
* transition decision in the state automaton.)
*/
static int
sppp_lcp_RCR(struct sppp *sp, struct lcp_header *h, int len)
{
STDDCL;
u_char *buf, *r, *p;
int origlen, rlen;
u_long nmagic;
u_short authproto;
len -= 4;
origlen = len;
buf = r = malloc (len, M_TEMP, M_NOWAIT);
if (! buf)
return (0);
if (debug)
log(LOG_DEBUG, SPP_FMT "lcp parse opts: ",
SPP_ARGS(ifp));
/* pass 1: check for things that need to be rejected */
p = (void*) (h+1);
for (rlen=0; len >= 2 && p[1] >= 2 && len >= p[1];
len-=p[1], p+=p[1]) {
if (debug)
log(-1, " %s ", sppp_lcp_opt_name(*p));
switch (*p) {
case LCP_OPT_MAGIC:
/* Magic number. */
if (len >= 6 && p[1] == 6)
continue;
if (debug)
log(-1, "[invalid] ");
break;
case LCP_OPT_ASYNC_MAP:
/* Async control character map. */
if (len >= 6 && p[1] == 6)
continue;
if (debug)
log(-1, "[invalid] ");
break;
case LCP_OPT_MRU:
/* Maximum receive unit. */
if (len >= 4 && p[1] == 4)
continue;
if (debug)
log(-1, "[invalid] ");
break;
case LCP_OPT_AUTH_PROTO:
if (len < 4) {
if (debug)
log(-1, "[invalid] ");
break;
}
authproto = (p[2] << 8) + p[3];
if (authproto == PPP_CHAP && p[1] != 5) {
if (debug)
log(-1, "[invalid chap len] ");
break;
}
if (sp->myauth.proto == 0) {
/* we are not configured to do auth */
if (debug)
log(-1, "[not configured] ");
break;
}
/*
* Remote want us to authenticate, remember this,
* so we stay in PHASE_AUTHENTICATE after LCP got
* up.
*/
sp->pp_flags |= PP_NEEDAUTH;
continue;
default:
/* Others not supported. */
if (debug)
log(-1, "[rej] ");
break;
}
/* Add the option to rejected list. */
bcopy (p, r, p[1]);
r += p[1];
rlen += p[1];
}
if (rlen) {
if (debug)
log(-1, " send conf-rej\n");
sppp_cp_send (sp, PPP_LCP, CONF_REJ, h->ident, rlen, buf);
return 0;
} else if (debug)
log(-1, "\n");
/*
* pass 2: check for option values that are unacceptable and
* thus require to be nak'ed.
*/
if (debug)
log(LOG_DEBUG, SPP_FMT "lcp parse opt values: ",
SPP_ARGS(ifp));
p = (void*) (h+1);
len = origlen;
for (rlen=0; len >= 2 && p[1] >= 2 && len >= p[1];
len-=p[1], p+=p[1]) {
if (debug)
log(-1, " %s ", sppp_lcp_opt_name(*p));
switch (*p) {
case LCP_OPT_MAGIC:
/* Magic number -- extract. */
nmagic = (u_long)p[2] << 24 |
(u_long)p[3] << 16 | p[4] << 8 | p[5];
if (nmagic != sp->lcp.magic) {
sp->pp_loopcnt = 0;
if (debug)
log(-1, "0x%lx ", nmagic);
continue;
}
if (debug && sp->pp_loopcnt < MAXALIVECNT*5)
log(-1, "[glitch] ");
++sp->pp_loopcnt;
/*
* We negate our magic here, and NAK it. If
* we see it later in an NAK packet, we
* suggest a new one.
*/
nmagic = ~sp->lcp.magic;
/* Gonna NAK it. */
p[2] = nmagic >> 24;
p[3] = nmagic >> 16;
p[4] = nmagic >> 8;
p[5] = nmagic;
break;
case LCP_OPT_ASYNC_MAP:
/*
* Async control character map -- just ignore it.
*
* Quote from RFC 1662, chapter 6:
* To enable this functionality, synchronous PPP
* implementations MUST always respond to the
* Async-Control-Character-Map Configuration
* Option with the LCP Configure-Ack. However,
* acceptance of the Configuration Option does
* not imply that the synchronous implementation
* will do any ACCM mapping. Instead, all such
* octet mapping will be performed by the
* asynchronous-to-synchronous converter.
*/
continue;
case LCP_OPT_MRU:
/*
* Maximum receive unit. Always agreeable,
* but ignored by now.
*/
sp->lcp.their_mru = p[2] * 256 + p[3];
if (debug)
log(-1, "%lu ", sp->lcp.their_mru);
continue;
case LCP_OPT_AUTH_PROTO:
authproto = (p[2] << 8) + p[3];
if (sp->myauth.proto != authproto) {
/* not agreed, nak */
if (debug)
log(-1, "[mine %s != his %s] ",
sppp_proto_name(sp->hisauth.proto),
sppp_proto_name(authproto));
p[2] = sp->myauth.proto >> 8;
p[3] = sp->myauth.proto;
break;
}
if (authproto == PPP_CHAP && p[4] != CHAP_MD5) {
if (debug)
log(-1, "[chap not MD5] ");
p[4] = CHAP_MD5;
break;
}
continue;
}
/* Add the option to nak'ed list. */
bcopy (p, r, p[1]);
r += p[1];
rlen += p[1];
}
if (rlen) {
/*
* Local and remote magics equal -- loopback?
*/
if (sp->pp_loopcnt >= MAXALIVECNT*5) {
if (sp->pp_loopcnt == MAXALIVECNT*5)
printf (SPP_FMT "loopback\n",
SPP_ARGS(ifp));
if (ifp->if_flags & IFF_UP) {
if_down(ifp);
sppp_qflush(&sp->pp_cpq);
/* XXX ? */
lcp.Down(sp);
lcp.Up(sp);
}
} else if (!sp->pp_loopcnt &&
++sp->fail_counter[IDX_LCP] >= sp->lcp.max_failure) {
if (debug)
log(-1, " max_failure (%d) exceeded, "
"send conf-rej\n",
sp->lcp.max_failure);
sppp_cp_send(sp, PPP_LCP, CONF_REJ, h->ident, rlen, buf);
} else {
if (debug)
log(-1, " send conf-nak\n");
sppp_cp_send (sp, PPP_LCP, CONF_NAK, h->ident, rlen, buf);
}
} else {
if (debug)
log(-1, " send conf-ack\n");
sp->fail_counter[IDX_LCP] = 0;
sp->pp_loopcnt = 0;
sppp_cp_send (sp, PPP_LCP, CONF_ACK,
h->ident, origlen, h+1);
}
free (buf, M_TEMP);
return (rlen == 0);
}
/*
* Analyze the LCP Configure-Reject option list, and adjust our
* negotiation.
*/
static void
sppp_lcp_RCN_rej(struct sppp *sp, struct lcp_header *h, int len)
{
STDDCL;
u_char *buf, *p;
len -= 4;
buf = malloc (len, M_TEMP, M_NOWAIT);
if (!buf)
return;
if (debug)
log(LOG_DEBUG, SPP_FMT "lcp rej opts: ",
SPP_ARGS(ifp));
p = (void*) (h+1);
for (; len >= 2 && p[1] >= 2 && len >= p[1];
len -= p[1], p += p[1]) {
if (debug)
log(-1, " %s ", sppp_lcp_opt_name(*p));
switch (*p) {
case LCP_OPT_MAGIC:
/* Magic number -- can't use it, use 0 */
sp->lcp.opts &= ~(1 << LCP_OPT_MAGIC);
sp->lcp.magic = 0;
break;
case LCP_OPT_MRU:
/*
* Should not be rejected anyway, since we only
* negotiate a MRU if explicitly requested by
* peer.
*/
sp->lcp.opts &= ~(1 << LCP_OPT_MRU);
break;
case LCP_OPT_AUTH_PROTO:
/*
* Peer doesn't want to authenticate himself,
* deny unless this is a dialout call, and
* AUTHFLAG_NOCALLOUT is set.
*/
if ((sp->pp_flags & PP_CALLIN) == 0 &&
(sp->hisauth.flags & AUTHFLAG_NOCALLOUT) != 0) {
if (debug)
log(-1, "[don't insist on auth "
"for callout]");
sp->lcp.opts &= ~(1 << LCP_OPT_AUTH_PROTO);
break;
}
if (debug)
log(-1, "[access denied]\n");
lcp.Close(sp);
break;
}
}
if (debug)
log(-1, "\n");
free (buf, M_TEMP);
return;
}
/*
* Analyze the LCP Configure-NAK option list, and adjust our
* negotiation.
*/
static void
sppp_lcp_RCN_nak(struct sppp *sp, struct lcp_header *h, int len)
{
STDDCL;
u_char *buf, *p;
u_long magic;
len -= 4;
buf = malloc (len, M_TEMP, M_NOWAIT);
if (!buf)
return;
if (debug)
log(LOG_DEBUG, SPP_FMT "lcp nak opts: ",
SPP_ARGS(ifp));
p = (void*) (h+1);
for (; len >= 2 && p[1] >= 2 && len >= p[1];
len -= p[1], p += p[1]) {
if (debug)
log(-1, " %s ", sppp_lcp_opt_name(*p));
switch (*p) {
case LCP_OPT_MAGIC:
/* Magic number -- renegotiate */
if ((sp->lcp.opts & (1 << LCP_OPT_MAGIC)) &&
len >= 6 && p[1] == 6) {
magic = (u_long)p[2] << 24 |
(u_long)p[3] << 16 | p[4] << 8 | p[5];
/*
* If the remote magic is our negated one,
* this looks like a loopback problem.
* Suggest a new magic to make sure.
*/
if (magic == ~sp->lcp.magic) {
if (debug)
log(-1, "magic glitch ");
sp->lcp.magic = random();
} else {
sp->lcp.magic = magic;
if (debug)
log(-1, "%lu ", magic);
}
}
break;
case LCP_OPT_MRU:
/*
* Peer wants to advise us to negotiate an MRU.
* Agree on it if it's reasonable, or use
* default otherwise.
*/
if (len >= 4 && p[1] == 4) {
u_int mru = p[2] * 256 + p[3];
if (debug)
log(-1, "%d ", mru);
if (mru < PP_MTU || mru > PP_MAX_MRU)
mru = PP_MTU;
sp->lcp.mru = mru;
sp->lcp.opts |= (1 << LCP_OPT_MRU);
}
break;
case LCP_OPT_AUTH_PROTO:
/*
* Peer doesn't like our authentication method,
* deny.
*/
if (debug)
log(-1, "[access denied]\n");
lcp.Close(sp);
break;
}
}
if (debug)
log(-1, "\n");
free (buf, M_TEMP);
return;
}
static void
sppp_lcp_tlu(struct sppp *sp)
{
STDDCL;
int i;
u_long mask;
/* XXX ? */
if (! (ifp->if_flags & IFF_UP) &&
(ifp->if_drv_flags & IFF_DRV_RUNNING)) {
/* Coming out of loopback mode. */
if_up(ifp);
printf (SPP_FMT "up\n", SPP_ARGS(ifp));
}
for (i = 0; i < IDX_COUNT; i++)
if ((cps[i])->flags & CP_QUAL)
(cps[i])->Open(sp);
if ((sp->lcp.opts & (1 << LCP_OPT_AUTH_PROTO)) != 0 ||
(sp->pp_flags & PP_NEEDAUTH) != 0)
sp->pp_phase = PHASE_AUTHENTICATE;
else
sp->pp_phase = PHASE_NETWORK;
if (debug)
log(LOG_DEBUG, SPP_FMT "phase %s\n", SPP_ARGS(ifp),
sppp_phase_name(sp->pp_phase));
/*
* Open all authentication protocols. This is even required
* if we already proceeded to network phase, since it might be
* that remote wants us to authenticate, so we might have to
* send a PAP request. Undesired authentication protocols
* don't do anything when they get an Open event.
*/
for (i = 0; i < IDX_COUNT; i++)
if ((cps[i])->flags & CP_AUTH)
(cps[i])->Open(sp);
if (sp->pp_phase == PHASE_NETWORK) {
/* Notify all NCPs. */
for (i = 0; i < IDX_COUNT; i++)
if (((cps[i])->flags & CP_NCP) &&
/*
* XXX
* Hack to administratively disable IPv6 if
* not desired. Perhaps we should have another
* flag for this, but right now, we can make
* all struct cp's read/only.
*/
(cps[i] != &ipv6cp ||
(sp->confflags & CONF_ENABLE_IPV6)))
(cps[i])->Open(sp);
}
/* Send Up events to all started protos. */
for (i = 0, mask = 1; i < IDX_COUNT; i++, mask <<= 1)
if ((sp->lcp.protos & mask) && ((cps[i])->flags & CP_LCP) == 0)
(cps[i])->Up(sp);
/* notify low-level driver of state change */
if (sp->pp_chg)
sp->pp_chg(sp, (int)sp->pp_phase);
if (sp->pp_phase == PHASE_NETWORK)
/* if no NCP is starting, close down */
sppp_lcp_check_and_close(sp);
}
static void
sppp_lcp_tld(struct sppp *sp)
{
STDDCL;
int i;
u_long mask;
sp->pp_phase = PHASE_TERMINATE;
if (debug)
log(LOG_DEBUG, SPP_FMT "phase %s\n", SPP_ARGS(ifp),
sppp_phase_name(sp->pp_phase));
/*
* Take upper layers down. We send the Down event first and
* the Close second to prevent the upper layers from sending
* ``a flurry of terminate-request packets'', as the RFC
* describes it.
*/
for (i = 0, mask = 1; i < IDX_COUNT; i++, mask <<= 1)
if ((sp->lcp.protos & mask) && ((cps[i])->flags & CP_LCP) == 0) {
(cps[i])->Down(sp);
(cps[i])->Close(sp);
}
}
static void
sppp_lcp_tls(struct sppp *sp)
{
STDDCL;
sp->pp_phase = PHASE_ESTABLISH;
if (debug)
log(LOG_DEBUG, SPP_FMT "phase %s\n", SPP_ARGS(ifp),
sppp_phase_name(sp->pp_phase));
/* Notify lower layer if desired. */
if (sp->pp_tls)
(sp->pp_tls)(sp);
else
(sp->pp_up)(sp);
}
static void
sppp_lcp_tlf(struct sppp *sp)
{
STDDCL;
sp->pp_phase = PHASE_DEAD;
if (debug)
log(LOG_DEBUG, SPP_FMT "phase %s\n", SPP_ARGS(ifp),
sppp_phase_name(sp->pp_phase));
/* Notify lower layer if desired. */
if (sp->pp_tlf)
(sp->pp_tlf)(sp);
else
(sp->pp_down)(sp);
}
static void
sppp_lcp_scr(struct sppp *sp)
{
char opt[6 /* magicnum */ + 4 /* mru */ + 5 /* chap */];
int i = 0;
u_short authproto;
if (sp->lcp.opts & (1 << LCP_OPT_MAGIC)) {
if (! sp->lcp.magic)
sp->lcp.magic = random();
opt[i++] = LCP_OPT_MAGIC;
opt[i++] = 6;
opt[i++] = sp->lcp.magic >> 24;
opt[i++] = sp->lcp.magic >> 16;
opt[i++] = sp->lcp.magic >> 8;
opt[i++] = sp->lcp.magic;
}
if (sp->lcp.opts & (1 << LCP_OPT_MRU)) {
opt[i++] = LCP_OPT_MRU;
opt[i++] = 4;
opt[i++] = sp->lcp.mru >> 8;
opt[i++] = sp->lcp.mru;
}
if (sp->lcp.opts & (1 << LCP_OPT_AUTH_PROTO)) {
authproto = sp->hisauth.proto;
opt[i++] = LCP_OPT_AUTH_PROTO;
opt[i++] = authproto == PPP_CHAP? 5: 4;
opt[i++] = authproto >> 8;
opt[i++] = authproto;
if (authproto == PPP_CHAP)
opt[i++] = CHAP_MD5;
}
sp->confid[IDX_LCP] = ++sp->pp_seq[IDX_LCP];
sppp_cp_send (sp, PPP_LCP, CONF_REQ, sp->confid[IDX_LCP], i, &opt);
}
/*
* Check the open NCPs, return true if at least one NCP is open.
*/
static int
sppp_ncp_check(struct sppp *sp)
{
int i, mask;
for (i = 0, mask = 1; i < IDX_COUNT; i++, mask <<= 1)
if ((sp->lcp.protos & mask) && (cps[i])->flags & CP_NCP)
return 1;
return 0;
}
/*
* Re-check the open NCPs and see if we should terminate the link.
* Called by the NCPs during their tlf action handling.
*/
static void
sppp_lcp_check_and_close(struct sppp *sp)
{
if (sp->pp_phase < PHASE_NETWORK)
/* don't bother, we are already going down */
return;
if (sppp_ncp_check(sp))
return;
lcp.Close(sp);
}
/*
*--------------------------------------------------------------------------*
* *
* The IPCP implementation. *
* *
*--------------------------------------------------------------------------*
*/
#ifdef INET
static void
sppp_ipcp_init(struct sppp *sp)
{
sp->ipcp.opts = 0;
sp->ipcp.flags = 0;
sp->state[IDX_IPCP] = STATE_INITIAL;
sp->fail_counter[IDX_IPCP] = 0;
sp->pp_seq[IDX_IPCP] = 0;
sp->pp_rseq[IDX_IPCP] = 0;
callout_init(&sp->ch[IDX_IPCP], 1);
}
static void
sppp_ipcp_up(struct sppp *sp)
{
sppp_up_event(&ipcp, sp);
}
static void
sppp_ipcp_down(struct sppp *sp)
{
sppp_down_event(&ipcp, sp);
}
static void
sppp_ipcp_open(struct sppp *sp)
{
STDDCL;
u_long myaddr, hisaddr;
sp->ipcp.flags &= ~(IPCP_HISADDR_SEEN | IPCP_MYADDR_SEEN |
IPCP_MYADDR_DYN | IPCP_VJ);
sp->ipcp.opts = 0;
sppp_get_ip_addrs(sp, &myaddr, &hisaddr, 0);
/*
* If we don't have his address, this probably means our
* interface doesn't want to talk IP at all. (This could
* be the case if somebody wants to speak only IPX, for
* example.) Don't open IPCP in this case.
*/
if (hisaddr == 0L) {
/* XXX this message should go away */
if (debug)
log(LOG_DEBUG, SPP_FMT "ipcp_open(): no IP interface\n",
SPP_ARGS(ifp));
return;
}
if (myaddr == 0L) {
/*
* I don't have an assigned address, so i need to
* negotiate my address.
*/
sp->ipcp.flags |= IPCP_MYADDR_DYN;
sp->ipcp.opts |= (1 << IPCP_OPT_ADDRESS);
} else
sp->ipcp.flags |= IPCP_MYADDR_SEEN;
if (sp->confflags & CONF_ENABLE_VJ) {
sp->ipcp.opts |= (1 << IPCP_OPT_COMPRESSION);
sp->ipcp.max_state = MAX_STATES - 1;
sp->ipcp.compress_cid = 1;
}
sppp_open_event(&ipcp, sp);
}
static void
sppp_ipcp_close(struct sppp *sp)
{
sppp_close_event(&ipcp, sp);
if (sp->ipcp.flags & IPCP_MYADDR_DYN)
/*
* My address was dynamic, clear it again.
*/
sppp_set_ip_addr(sp, 0L);
}
static void
sppp_ipcp_TO(void *cookie)
{
sppp_to_event(&ipcp, (struct sppp *)cookie);
}
/*
* Analyze a configure request. Return true if it was agreeable, and
* caused action sca, false if it has been rejected or nak'ed, and
* caused action scn. (The return value is used to make the state
* transition decision in the state automaton.)
*/
static int
sppp_ipcp_RCR(struct sppp *sp, struct lcp_header *h, int len)
{
u_char *buf, *r, *p;
struct ifnet *ifp = SP2IFP(sp);
int rlen, origlen, debug = ifp->if_flags & IFF_DEBUG;
u_long hisaddr, desiredaddr;
int gotmyaddr = 0;
int desiredcomp;
len -= 4;
origlen = len;
/*
* Make sure to allocate a buf that can at least hold a
* conf-nak with an `address' option. We might need it below.
*/
buf = r = malloc ((len < 6? 6: len), M_TEMP, M_NOWAIT);
if (! buf)
return (0);
/* pass 1: see if we can recognize them */
if (debug)
log(LOG_DEBUG, SPP_FMT "ipcp parse opts: ",
SPP_ARGS(ifp));
p = (void*) (h+1);
for (rlen=0; len >= 2 && p[1] >= 2 && len >= p[1];
len-=p[1], p+=p[1]) {
if (debug)
log(-1, " %s ", sppp_ipcp_opt_name(*p));
switch (*p) {
case IPCP_OPT_COMPRESSION:
if (!(sp->confflags & CONF_ENABLE_VJ)) {
/* VJ compression administratively disabled */
if (debug)
log(-1, "[locally disabled] ");
break;
}
/*
* In theory, we should only conf-rej an
* option that is shorter than RFC 1618
* requires (i.e. < 4), and should conf-nak
* anything else that is not VJ. However,
* since our algorithm always uses the
* original option to NAK it with new values,
* things would become more complicated. In
* practice, the only commonly implemented IP
* compression option is VJ anyway, so the
* difference is negligible.
*/
if (len >= 6 && p[1] == 6) {
/*
* correctly formed compression option
* that could be VJ compression
*/
continue;
}
if (debug)
log(-1,
"optlen %d [invalid/unsupported] ",
p[1]);
break;
case IPCP_OPT_ADDRESS:
if (len >= 6 && p[1] == 6) {
/* correctly formed address option */
continue;
}
if (debug)
log(-1, "[invalid] ");
break;
default:
/* Others not supported. */
if (debug)
log(-1, "[rej] ");
break;
}
/* Add the option to rejected list. */
bcopy (p, r, p[1]);
r += p[1];
rlen += p[1];
}
if (rlen) {
if (debug)
log(-1, " send conf-rej\n");
sppp_cp_send (sp, PPP_IPCP, CONF_REJ, h->ident, rlen, buf);
return 0;
} else if (debug)
log(-1, "\n");
/* pass 2: parse option values */
sppp_get_ip_addrs(sp, 0, &hisaddr, 0);
if (debug)
log(LOG_DEBUG, SPP_FMT "ipcp parse opt values: ",
SPP_ARGS(ifp));
p = (void*) (h+1);
len = origlen;
for (rlen=0; len >= 2 && p[1] >= 2 && len >= p[1];
len-=p[1], p+=p[1]) {
if (debug)
log(-1, " %s ", sppp_ipcp_opt_name(*p));
switch (*p) {
case IPCP_OPT_COMPRESSION:
desiredcomp = p[2] << 8 | p[3];
/* We only support VJ */
if (desiredcomp == IPCP_COMP_VJ) {
if (debug)
log(-1, "VJ [ack] ");
sp->ipcp.flags |= IPCP_VJ;
sl_compress_init(sp->pp_comp, p[4]);
sp->ipcp.max_state = p[4];
sp->ipcp.compress_cid = p[5];
continue;
}
if (debug)
log(-1,
"compproto %#04x [not supported] ",
desiredcomp);
p[2] = IPCP_COMP_VJ >> 8;
p[3] = IPCP_COMP_VJ;
p[4] = sp->ipcp.max_state;
p[5] = sp->ipcp.compress_cid;
break;
case IPCP_OPT_ADDRESS:
/* This is the address he wants in his end */
desiredaddr = p[2] << 24 | p[3] << 16 |
p[4] << 8 | p[5];
if (desiredaddr == hisaddr ||
(hisaddr >= 1 && hisaddr <= 254 && desiredaddr != 0)) {
/*
* Peer's address is same as our value,
* or we have set it to 0.0.0.* to
* indicate that we do not really care,
* this is agreeable. Gonna conf-ack
* it.
*/
if (debug)
log(-1, "%s [ack] ",
sppp_dotted_quad(hisaddr));
/* record that we've seen it already */
sp->ipcp.flags |= IPCP_HISADDR_SEEN;
continue;
}
/*
* The address wasn't agreeable. This is either
* he sent us 0.0.0.0, asking to assign him an
* address, or he send us another address not
* matching our value. Either case, we gonna
* conf-nak it with our value.
* XXX: we should "rej" if hisaddr == 0
*/
if (debug) {
if (desiredaddr == 0)
log(-1, "[addr requested] ");
else
log(-1, "%s [not agreed] ",
sppp_dotted_quad(desiredaddr));
}
p[2] = hisaddr >> 24;
p[3] = hisaddr >> 16;
p[4] = hisaddr >> 8;
p[5] = hisaddr;
break;
}
/* Add the option to nak'ed list. */
bcopy (p, r, p[1]);
r += p[1];
rlen += p[1];
}
/*
* If we are about to conf-ack the request, but haven't seen
* his address so far, gonna conf-nak it instead, with the
* `address' option present and our idea of his address being
* filled in there, to request negotiation of both addresses.
*
* XXX This can result in an endless req - nak loop if peer
* doesn't want to send us his address. Q: What should we do
* about it? XXX A: implement the max-failure counter.
*/
if (rlen == 0 && !(sp->ipcp.flags & IPCP_HISADDR_SEEN) && !gotmyaddr) {
buf[0] = IPCP_OPT_ADDRESS;
buf[1] = 6;
buf[2] = hisaddr >> 24;
buf[3] = hisaddr >> 16;
buf[4] = hisaddr >> 8;
buf[5] = hisaddr;
rlen = 6;
if (debug)
log(-1, "still need hisaddr ");
}
if (rlen) {
if (debug)
log(-1, " send conf-nak\n");
sppp_cp_send (sp, PPP_IPCP, CONF_NAK, h->ident, rlen, buf);
} else {
if (debug)
log(-1, " send conf-ack\n");
sppp_cp_send (sp, PPP_IPCP, CONF_ACK,
h->ident, origlen, h+1);
}
free (buf, M_TEMP);
return (rlen == 0);
}
/*
* Analyze the IPCP Configure-Reject option list, and adjust our
* negotiation.
*/
static void
sppp_ipcp_RCN_rej(struct sppp *sp, struct lcp_header *h, int len)
{
u_char *buf, *p;
struct ifnet *ifp = SP2IFP(sp);
int debug = ifp->if_flags & IFF_DEBUG;
len -= 4;
buf = malloc (len, M_TEMP, M_NOWAIT);
if (!buf)
return;
if (debug)
log(LOG_DEBUG, SPP_FMT "ipcp rej opts: ",
SPP_ARGS(ifp));
p = (void*) (h+1);
for (; len >= 2 && p[1] >= 2 && len >= p[1];
len -= p[1], p += p[1]) {
if (debug)
log(-1, " %s ", sppp_ipcp_opt_name(*p));
switch (*p) {
case IPCP_OPT_COMPRESSION:
sp->ipcp.opts &= ~(1 << IPCP_OPT_COMPRESSION);
break;
case IPCP_OPT_ADDRESS:
/*
* Peer doesn't grok address option. This is
* bad. XXX Should we better give up here?
* XXX We could try old "addresses" option...
*/
sp->ipcp.opts &= ~(1 << IPCP_OPT_ADDRESS);
break;
}
}
if (debug)
log(-1, "\n");
free (buf, M_TEMP);
return;
}
/*
* Analyze the IPCP Configure-NAK option list, and adjust our
* negotiation.
*/
static void
sppp_ipcp_RCN_nak(struct sppp *sp, struct lcp_header *h, int len)
{
u_char *buf, *p;
struct ifnet *ifp = SP2IFP(sp);
int debug = ifp->if_flags & IFF_DEBUG;
int desiredcomp;
u_long wantaddr;
len -= 4;
buf = malloc (len, M_TEMP, M_NOWAIT);
if (!buf)
return;
if (debug)
log(LOG_DEBUG, SPP_FMT "ipcp nak opts: ",
SPP_ARGS(ifp));
p = (void*) (h+1);
for (; len >= 2 && p[1] >= 2 && len >= p[1];
len -= p[1], p += p[1]) {
if (debug)
log(-1, " %s ", sppp_ipcp_opt_name(*p));
switch (*p) {
case IPCP_OPT_COMPRESSION:
if (len >= 6 && p[1] == 6) {
desiredcomp = p[2] << 8 | p[3];
if (debug)
log(-1, "[wantcomp %#04x] ",
desiredcomp);
if (desiredcomp == IPCP_COMP_VJ) {
sl_compress_init(sp->pp_comp, p[4]);
sp->ipcp.max_state = p[4];
sp->ipcp.compress_cid = p[5];
if (debug)
log(-1, "[agree] ");
} else
sp->ipcp.opts &=
~(1 << IPCP_OPT_COMPRESSION);
}
break;
case IPCP_OPT_ADDRESS:
/*
* Peer doesn't like our local IP address. See
* if we can do something for him. We'll drop
* him our address then.
*/
if (len >= 6 && p[1] == 6) {
wantaddr = p[2] << 24 | p[3] << 16 |
p[4] << 8 | p[5];
sp->ipcp.opts |= (1 << IPCP_OPT_ADDRESS);
if (debug)
log(-1, "[wantaddr %s] ",
sppp_dotted_quad(wantaddr));
/*
* When doing dynamic address assignment,
* we accept his offer. Otherwise, we
* ignore it and thus continue to negotiate
* our already existing value.
* XXX: Bogus, if he said no once, he'll
* just say no again, might as well die.
*/
if (sp->ipcp.flags & IPCP_MYADDR_DYN) {
sppp_set_ip_addr(sp, wantaddr);
if (debug)
log(-1, "[agree] ");
sp->ipcp.flags |= IPCP_MYADDR_SEEN;
}
}
break;
}
}
if (debug)
log(-1, "\n");
free (buf, M_TEMP);
return;
}
static void
sppp_ipcp_tlu(struct sppp *sp)
{
/* we are up - notify isdn daemon */
if (sp->pp_con)
sp->pp_con(sp);
}
static void
sppp_ipcp_tld(struct sppp *sp)
{
}
static void
sppp_ipcp_tls(struct sppp *sp)
{
/* indicate to LCP that it must stay alive */
sp->lcp.protos |= (1 << IDX_IPCP);
}
static void
sppp_ipcp_tlf(struct sppp *sp)
{
/* we no longer need LCP */
sp->lcp.protos &= ~(1 << IDX_IPCP);
sppp_lcp_check_and_close(sp);
}
static void
sppp_ipcp_scr(struct sppp *sp)
{
char opt[6 /* compression */ + 6 /* address */];
u_long ouraddr;
int i = 0;
if (sp->ipcp.opts & (1 << IPCP_OPT_COMPRESSION)) {
opt[i++] = IPCP_OPT_COMPRESSION;
opt[i++] = 6;
opt[i++] = IPCP_COMP_VJ >> 8;
opt[i++] = IPCP_COMP_VJ;
opt[i++] = sp->ipcp.max_state;
opt[i++] = sp->ipcp.compress_cid;
}
if (sp->ipcp.opts & (1 << IPCP_OPT_ADDRESS)) {
sppp_get_ip_addrs(sp, &ouraddr, 0, 0);
opt[i++] = IPCP_OPT_ADDRESS;
opt[i++] = 6;
opt[i++] = ouraddr >> 24;
opt[i++] = ouraddr >> 16;
opt[i++] = ouraddr >> 8;
opt[i++] = ouraddr;
}
sp->confid[IDX_IPCP] = ++sp->pp_seq[IDX_IPCP];
sppp_cp_send(sp, PPP_IPCP, CONF_REQ, sp->confid[IDX_IPCP], i, &opt);
}
#else /* !INET */
static void
sppp_ipcp_init(struct sppp *sp)
{
}
static void
sppp_ipcp_up(struct sppp *sp)
{
}
static void
sppp_ipcp_down(struct sppp *sp)
{
}
static void
sppp_ipcp_open(struct sppp *sp)
{
}
static void
sppp_ipcp_close(struct sppp *sp)
{
}
static void
sppp_ipcp_TO(void *cookie)
{
}
static int
sppp_ipcp_RCR(struct sppp *sp, struct lcp_header *h, int len)
{
return (0);
}
static void
sppp_ipcp_RCN_rej(struct sppp *sp, struct lcp_header *h, int len)
{
}
static void
sppp_ipcp_RCN_nak(struct sppp *sp, struct lcp_header *h, int len)
{
}
static void
sppp_ipcp_tlu(struct sppp *sp)
{
}
static void
sppp_ipcp_tld(struct sppp *sp)
{
}
static void
sppp_ipcp_tls(struct sppp *sp)
{
}
static void
sppp_ipcp_tlf(struct sppp *sp)
{
}
static void
sppp_ipcp_scr(struct sppp *sp)
{
}
#endif
/*
*--------------------------------------------------------------------------*
* *
* The IPv6CP implementation. *
* *
*--------------------------------------------------------------------------*
*/
#ifdef INET6
static void
sppp_ipv6cp_init(struct sppp *sp)
{
sp->ipv6cp.opts = 0;
sp->ipv6cp.flags = 0;
sp->state[IDX_IPV6CP] = STATE_INITIAL;
sp->fail_counter[IDX_IPV6CP] = 0;
sp->pp_seq[IDX_IPV6CP] = 0;
sp->pp_rseq[IDX_IPV6CP] = 0;
callout_init(&sp->ch[IDX_IPV6CP], 1);
}
static void
sppp_ipv6cp_up(struct sppp *sp)
{
sppp_up_event(&ipv6cp, sp);
}
static void
sppp_ipv6cp_down(struct sppp *sp)
{
sppp_down_event(&ipv6cp, sp);
}
static void
sppp_ipv6cp_open(struct sppp *sp)
{
STDDCL;
struct in6_addr myaddr, hisaddr;
#ifdef IPV6CP_MYIFID_DYN
sp->ipv6cp.flags &= ~(IPV6CP_MYIFID_SEEN|IPV6CP_MYIFID_DYN);
#else
sp->ipv6cp.flags &= ~IPV6CP_MYIFID_SEEN;
#endif
sppp_get_ip6_addrs(sp, &myaddr, &hisaddr, 0);
/*
* If we don't have our address, this probably means our
* interface doesn't want to talk IPv6 at all. (This could
* be the case if somebody wants to speak only IPX, for
* example.) Don't open IPv6CP in this case.
*/
if (IN6_IS_ADDR_UNSPECIFIED(&myaddr)) {
/* XXX this message should go away */
if (debug)
log(LOG_DEBUG, SPP_FMT "ipv6cp_open(): no IPv6 interface\n",
SPP_ARGS(ifp));
return;
}
sp->ipv6cp.flags |= IPV6CP_MYIFID_SEEN;
sp->ipv6cp.opts |= (1 << IPV6CP_OPT_IFID);
sppp_open_event(&ipv6cp, sp);
}
static void
sppp_ipv6cp_close(struct sppp *sp)
{
sppp_close_event(&ipv6cp, sp);
}
static void
sppp_ipv6cp_TO(void *cookie)
{
sppp_to_event(&ipv6cp, (struct sppp *)cookie);
}
/*
* Analyze a configure request. Return true if it was agreeable, and
* caused action sca, false if it has been rejected or nak'ed, and
* caused action scn. (The return value is used to make the state
* transition decision in the state automaton.)
*/
static int
sppp_ipv6cp_RCR(struct sppp *sp, struct lcp_header *h, int len)
{
u_char *buf, *r, *p;
struct ifnet *ifp = SP2IFP(sp);
int rlen, origlen, debug = ifp->if_flags & IFF_DEBUG;
struct in6_addr myaddr, desiredaddr, suggestaddr;
int ifidcount;
int type;
int collision, nohisaddr;
char ip6buf[INET6_ADDRSTRLEN];
len -= 4;
origlen = len;
/*
* Make sure to allocate a buf that can at least hold a
* conf-nak with an `address' option. We might need it below.
*/
buf = r = malloc ((len < 6? 6: len), M_TEMP, M_NOWAIT);
if (! buf)
return (0);
/* pass 1: see if we can recognize them */
if (debug)
log(LOG_DEBUG, SPP_FMT "ipv6cp parse opts:",
SPP_ARGS(ifp));
p = (void*) (h+1);
ifidcount = 0;
for (rlen=0; len >= 2 && p[1] >= 2 && len >= p[1];
len-=p[1], p+=p[1]) {
if (debug)
log(-1, " %s", sppp_ipv6cp_opt_name(*p));
switch (*p) {
case IPV6CP_OPT_IFID:
if (len >= 10 && p[1] == 10 && ifidcount == 0) {
/* correctly formed address option */
ifidcount++;
continue;
}
if (debug)
log(-1, " [invalid]");
break;
#ifdef notyet
case IPV6CP_OPT_COMPRESSION:
if (len >= 4 && p[1] >= 4) {
/* correctly formed compress option */
continue;
}
if (debug)
log(-1, " [invalid]");
break;
#endif
default:
/* Others not supported. */
if (debug)
log(-1, " [rej]");
break;
}
/* Add the option to rejected list. */
bcopy (p, r, p[1]);
r += p[1];
rlen += p[1];
}
if (rlen) {
if (debug)
log(-1, " send conf-rej\n");
sppp_cp_send (sp, PPP_IPV6CP, CONF_REJ, h->ident, rlen, buf);
goto end;
} else if (debug)
log(-1, "\n");
/* pass 2: parse option values */
sppp_get_ip6_addrs(sp, &myaddr, 0, 0);
if (debug)
log(LOG_DEBUG, SPP_FMT "ipv6cp parse opt values: ",
SPP_ARGS(ifp));
p = (void*) (h+1);
len = origlen;
type = CONF_ACK;
for (rlen=0; len >= 2 && p[1] >= 2 && len >= p[1];
len-=p[1], p+=p[1]) {
if (debug)
log(-1, " %s", sppp_ipv6cp_opt_name(*p));
switch (*p) {
#ifdef notyet
case IPV6CP_OPT_COMPRESSION:
continue;
#endif
case IPV6CP_OPT_IFID:
bzero(&desiredaddr, sizeof(desiredaddr));
bcopy(&p[2], &desiredaddr.s6_addr[8], 8);
collision = (bcmp(&desiredaddr.s6_addr[8],
&myaddr.s6_addr[8], 8) == 0);
nohisaddr = IN6_IS_ADDR_UNSPECIFIED(&desiredaddr);
desiredaddr.s6_addr16[0] = htons(0xfe80);
(void)in6_setscope(&desiredaddr, SP2IFP(sp), NULL);
if (!collision && !nohisaddr) {
/* no collision, hisaddr known - Conf-Ack */
type = CONF_ACK;
if (debug) {
log(-1, " %s [%s]",
ip6_sprintf(ip6buf, &desiredaddr),
sppp_cp_type_name(type));
}
continue;
}
bzero(&suggestaddr, sizeof(suggestaddr));
if (collision && nohisaddr) {
/* collision, hisaddr unknown - Conf-Rej */
type = CONF_REJ;
bzero(&p[2], 8);
} else {
/*
* - no collision, hisaddr unknown, or
* - collision, hisaddr known
* Conf-Nak, suggest hisaddr
*/
type = CONF_NAK;
sppp_suggest_ip6_addr(sp, &suggestaddr);
bcopy(&suggestaddr.s6_addr[8], &p[2], 8);
}
if (debug)
log(-1, " %s [%s]",
ip6_sprintf(ip6buf, &desiredaddr),
sppp_cp_type_name(type));
break;
}
/* Add the option to nak'ed list. */
bcopy (p, r, p[1]);
r += p[1];
rlen += p[1];
}
if (rlen == 0 && type == CONF_ACK) {
if (debug)
log(-1, " send %s\n", sppp_cp_type_name(type));
sppp_cp_send (sp, PPP_IPV6CP, type, h->ident, origlen, h+1);
} else {
#ifdef DIAGNOSTIC
if (type == CONF_ACK)
panic("IPv6CP RCR: CONF_ACK with non-zero rlen");
#endif
if (debug) {
log(-1, " send %s suggest %s\n",
sppp_cp_type_name(type),
ip6_sprintf(ip6buf, &suggestaddr));
}
sppp_cp_send (sp, PPP_IPV6CP, type, h->ident, rlen, buf);
}
end:
free (buf, M_TEMP);
return (rlen == 0);
}
/*
* Analyze the IPv6CP Configure-Reject option list, and adjust our
* negotiation.
*/
static void
sppp_ipv6cp_RCN_rej(struct sppp *sp, struct lcp_header *h, int len)
{
u_char *buf, *p;
struct ifnet *ifp = SP2IFP(sp);
int debug = ifp->if_flags & IFF_DEBUG;
len -= 4;
buf = malloc (len, M_TEMP, M_NOWAIT);
if (!buf)
return;
if (debug)
log(LOG_DEBUG, SPP_FMT "ipv6cp rej opts:",
SPP_ARGS(ifp));
p = (void*) (h+1);
for (; len >= 2 && p[1] >= 2 && len >= p[1];
len -= p[1], p += p[1]) {
if (debug)
log(-1, " %s", sppp_ipv6cp_opt_name(*p));
switch (*p) {
case IPV6CP_OPT_IFID:
/*
* Peer doesn't grok address option. This is
* bad. XXX Should we better give up here?
*/
sp->ipv6cp.opts &= ~(1 << IPV6CP_OPT_IFID);
break;
#ifdef notyet
case IPV6CP_OPT_COMPRESS:
sp->ipv6cp.opts &= ~(1 << IPV6CP_OPT_COMPRESS);
break;
#endif
}
}
if (debug)
log(-1, "\n");
free (buf, M_TEMP);
return;
}
/*
* Analyze the IPv6CP Configure-NAK option list, and adjust our
* negotiation.
*/
static void
sppp_ipv6cp_RCN_nak(struct sppp *sp, struct lcp_header *h, int len)
{
u_char *buf, *p;
struct ifnet *ifp = SP2IFP(sp);
int debug = ifp->if_flags & IFF_DEBUG;
struct in6_addr suggestaddr;
char ip6buf[INET6_ADDRSTRLEN];
len -= 4;
buf = malloc (len, M_TEMP, M_NOWAIT);
if (!buf)
return;
if (debug)
log(LOG_DEBUG, SPP_FMT "ipv6cp nak opts:",
SPP_ARGS(ifp));
p = (void*) (h+1);
for (; len >= 2 && p[1] >= 2 && len >= p[1];
len -= p[1], p += p[1]) {
if (debug)
log(-1, " %s", sppp_ipv6cp_opt_name(*p));
switch (*p) {
case IPV6CP_OPT_IFID:
/*
* Peer doesn't like our local ifid. See
* if we can do something for him. We'll drop
* him our address then.
*/
if (len < 10 || p[1] != 10)
break;
bzero(&suggestaddr, sizeof(suggestaddr));
suggestaddr.s6_addr16[0] = htons(0xfe80);
(void)in6_setscope(&suggestaddr, SP2IFP(sp), NULL);
bcopy(&p[2], &suggestaddr.s6_addr[8], 8);
sp->ipv6cp.opts |= (1 << IPV6CP_OPT_IFID);
if (debug)
log(-1, " [suggestaddr %s]",
ip6_sprintf(ip6buf, &suggestaddr));
#ifdef IPV6CP_MYIFID_DYN
/*
* When doing dynamic address assignment,
* we accept his offer.
*/
if (sp->ipv6cp.flags & IPV6CP_MYIFID_DYN) {
struct in6_addr lastsuggest;
/*
* If <suggested myaddr from peer> equals to
* <hisaddr we have suggested last time>,
* we have a collision. generate new random
* ifid.
*/
sppp_suggest_ip6_addr(&lastsuggest);
if (IN6_ARE_ADDR_EQUAL(&suggestaddr,
lastsuggest)) {
if (debug)
log(-1, " [random]");
sppp_gen_ip6_addr(sp, &suggestaddr);
}
sppp_set_ip6_addr(sp, &suggestaddr, 0);
if (debug)
log(-1, " [agree]");
sp->ipv6cp.flags |= IPV6CP_MYIFID_SEEN;
}
#else
/*
* Since we do not do dynamic address assignment,
* we ignore it and thus continue to negotiate
* our already existing value. This can possibly
* go into infinite request-reject loop.
*
* This is not likely because we normally use
* ifid based on MAC-address.
* If you have no ethernet card on the node, too bad.
* XXX should we use fail_counter?
*/
#endif
break;
#ifdef notyet
case IPV6CP_OPT_COMPRESS:
/*
* Peer wants different compression parameters.
*/
break;
#endif
}
}
if (debug)
log(-1, "\n");
free (buf, M_TEMP);
return;
}
static void
sppp_ipv6cp_tlu(struct sppp *sp)
{
/* we are up - notify isdn daemon */
if (sp->pp_con)
sp->pp_con(sp);
}
static void
sppp_ipv6cp_tld(struct sppp *sp)
{
}
static void
sppp_ipv6cp_tls(struct sppp *sp)
{
/* indicate to LCP that it must stay alive */
sp->lcp.protos |= (1 << IDX_IPV6CP);
}
static void
sppp_ipv6cp_tlf(struct sppp *sp)
{
#if 0 /* need #if 0 to close IPv6CP properly */
/* we no longer need LCP */
sp->lcp.protos &= ~(1 << IDX_IPV6CP);
sppp_lcp_check_and_close(sp);
#endif
}
static void
sppp_ipv6cp_scr(struct sppp *sp)
{
char opt[10 /* ifid */ + 4 /* compression, minimum */];
struct in6_addr ouraddr;
int i = 0;
if (sp->ipv6cp.opts & (1 << IPV6CP_OPT_IFID)) {
sppp_get_ip6_addrs(sp, &ouraddr, 0, 0);
opt[i++] = IPV6CP_OPT_IFID;
opt[i++] = 10;
bcopy(&ouraddr.s6_addr[8], &opt[i], 8);
i += 8;
}
#ifdef notyet
if (sp->ipv6cp.opts & (1 << IPV6CP_OPT_COMPRESSION)) {
opt[i++] = IPV6CP_OPT_COMPRESSION;
opt[i++] = 4;
opt[i++] = 0; /* TBD */
opt[i++] = 0; /* TBD */
/* variable length data may follow */
}
#endif
sp->confid[IDX_IPV6CP] = ++sp->pp_seq[IDX_IPV6CP];
sppp_cp_send(sp, PPP_IPV6CP, CONF_REQ, sp->confid[IDX_IPV6CP], i, &opt);
}
#else /*INET6*/
static void sppp_ipv6cp_init(struct sppp *sp)
{
}
static void sppp_ipv6cp_up(struct sppp *sp)
{
}
static void sppp_ipv6cp_down(struct sppp *sp)
{
}
static void sppp_ipv6cp_open(struct sppp *sp)
{
}
static void sppp_ipv6cp_close(struct sppp *sp)
{
}
static void sppp_ipv6cp_TO(void *sp)
{
}
static int sppp_ipv6cp_RCR(struct sppp *sp, struct lcp_header *h, int len)
{
return 0;
}
static void sppp_ipv6cp_RCN_rej(struct sppp *sp, struct lcp_header *h, int len)
{
}
static void sppp_ipv6cp_RCN_nak(struct sppp *sp, struct lcp_header *h, int len)
{
}
static void sppp_ipv6cp_tlu(struct sppp *sp)
{
}
static void sppp_ipv6cp_tld(struct sppp *sp)
{
}
static void sppp_ipv6cp_tls(struct sppp *sp)
{
}
static void sppp_ipv6cp_tlf(struct sppp *sp)
{
}
static void sppp_ipv6cp_scr(struct sppp *sp)
{
}
#endif /*INET6*/
/*
*--------------------------------------------------------------------------*
* *
* The CHAP implementation. *
* *
*--------------------------------------------------------------------------*
*/
/*
* The authentication protocols don't employ a full-fledged state machine as
* the control protocols do, since they do have Open and Close events, but
* not Up and Down, nor are they explicitly terminated. Also, use of the
* authentication protocols may be different in both directions (this makes
* sense, think of a machine that never accepts incoming calls but only
* calls out, it doesn't require the called party to authenticate itself).
*
* Our state machine for the local authentication protocol (we are requesting
* the peer to authenticate) looks like:
*
* RCA-
* +--------------------------------------------+
* V scn,tld|
* +--------+ Close +---------+ RCA+
* | |<----------------------------------| |------+
* +--->| Closed | TO* | Opened | sca |
* | | |-----+ +-------| |<-----+
* | +--------+ irc | | +---------+
* | ^ | | ^
* | | | | |
* | | | | |
* | TO-| | | |
* | |tld TO+ V | |
* | | +------->+ | |
* | | | | | |
* | +--------+ V | |
* | | |<----+<--------------------+ |
* | | Req- | scr |
* | | Sent | |
* | | | |
* | +--------+ |
* | RCA- | | RCA+ |
* +------+ +------------------------------------------+
* scn,tld sca,irc,ict,tlu
*
*
* with:
*
* Open: LCP reached authentication phase
* Close: LCP reached terminate phase
*
* RCA+: received reply (pap-req, chap-response), acceptable
* RCN: received reply (pap-req, chap-response), not acceptable
* TO+: timeout with restart counter >= 0
* TO-: timeout with restart counter < 0
* TO*: reschedule timeout for CHAP
*
* scr: send request packet (none for PAP, chap-challenge)
* sca: send ack packet (pap-ack, chap-success)
* scn: send nak packet (pap-nak, chap-failure)
* ict: initialize re-challenge timer (CHAP only)
*
* tlu: this-layer-up, LCP reaches network phase
* tld: this-layer-down, LCP enters terminate phase
*
* Note that in CHAP mode, after sending a new challenge, while the state
* automaton falls back into Req-Sent state, it doesn't signal a tld
* event to LCP, so LCP remains in network phase. Only after not getting
* any response (or after getting an unacceptable response), CHAP closes,
* causing LCP to enter terminate phase.
*
* With PAP, there is no initial request that can be sent. The peer is
* expected to send one based on the successful negotiation of PAP as
* the authentication protocol during the LCP option negotiation.
*
* Incoming authentication protocol requests (remote requests
* authentication, we are peer) don't employ a state machine at all,
* they are simply answered. Some peers [Ascend P50 firmware rev
* 4.50] react allergically when sending IPCP requests while they are
* still in authentication phase (thereby violating the standard that
* demands that these NCP packets are to be discarded), so we keep
* track of the peer demanding us to authenticate, and only proceed to
* phase network once we've seen a positive acknowledge for the
* authentication.
*/
/*
* Handle incoming CHAP packets.
*/
static void
sppp_chap_input(struct sppp *sp, struct mbuf *m)
{
STDDCL;
struct lcp_header *h;
int len;
u_char *value, *name, digest[AUTHKEYLEN], dsize;
int value_len, name_len;
MD5_CTX ctx;
len = m->m_pkthdr.len;
if (len < 4) {
if (debug)
log(LOG_DEBUG,
SPP_FMT "chap invalid packet length: %d bytes\n",
SPP_ARGS(ifp), len);
return;
}
h = mtod (m, struct lcp_header*);
if (len > ntohs (h->len))
len = ntohs (h->len);
switch (h->type) {
/* challenge, failure and success are his authproto */
case CHAP_CHALLENGE:
value = 1 + (u_char*)(h+1);
value_len = value[-1];
name = value + value_len;
name_len = len - value_len - 5;
if (name_len < 0) {
if (debug) {
log(LOG_DEBUG,
SPP_FMT "chap corrupted challenge "
"<%s id=0x%x len=%d",
SPP_ARGS(ifp),
sppp_auth_type_name(PPP_CHAP, h->type),
h->ident, ntohs(h->len));
sppp_print_bytes((u_char*) (h+1), len-4);
log(-1, ">\n");
}
break;
}
if (debug) {
log(LOG_DEBUG,
SPP_FMT "chap input <%s id=0x%x len=%d name=",
SPP_ARGS(ifp),
sppp_auth_type_name(PPP_CHAP, h->type), h->ident,
ntohs(h->len));
sppp_print_string((char*) name, name_len);
log(-1, " value-size=%d value=", value_len);
sppp_print_bytes(value, value_len);
log(-1, ">\n");
}
/* Compute reply value. */
MD5Init(&ctx);
MD5Update(&ctx, &h->ident, 1);
MD5Update(&ctx, sp->myauth.secret,
sppp_strnlen(sp->myauth.secret, AUTHKEYLEN));
MD5Update(&ctx, value, value_len);
MD5Final(digest, &ctx);
dsize = sizeof digest;
sppp_auth_send(&chap, sp, CHAP_RESPONSE, h->ident,
sizeof dsize, (const char *)&dsize,
sizeof digest, digest,
(size_t)sppp_strnlen(sp->myauth.name, AUTHNAMELEN),
sp->myauth.name,
0);
break;
case CHAP_SUCCESS:
if (debug) {
log(LOG_DEBUG, SPP_FMT "chap success",
SPP_ARGS(ifp));
if (len > 4) {
log(-1, ": ");
sppp_print_string((char*)(h + 1), len - 4);
}
log(-1, "\n");
}
SPPP_LOCK(sp);
sp->pp_flags &= ~PP_NEEDAUTH;
if (sp->myauth.proto == PPP_CHAP &&
(sp->lcp.opts & (1 << LCP_OPT_AUTH_PROTO)) &&
(sp->lcp.protos & (1 << IDX_CHAP)) == 0) {
/*
* We are authenticator for CHAP but didn't
* complete yet. Leave it to tlu to proceed
* to network phase.
*/
SPPP_UNLOCK(sp);
break;
}
SPPP_UNLOCK(sp);
sppp_phase_network(sp);
break;
case CHAP_FAILURE:
if (debug) {
log(LOG_INFO, SPP_FMT "chap failure",
SPP_ARGS(ifp));
if (len > 4) {
log(-1, ": ");
sppp_print_string((char*)(h + 1), len - 4);
}
log(-1, "\n");
} else
log(LOG_INFO, SPP_FMT "chap failure\n",
SPP_ARGS(ifp));
/* await LCP shutdown by authenticator */
break;
/* response is my authproto */
case CHAP_RESPONSE:
value = 1 + (u_char*)(h+1);
value_len = value[-1];
name = value + value_len;
name_len = len - value_len - 5;
if (name_len < 0) {
if (debug) {
log(LOG_DEBUG,
SPP_FMT "chap corrupted response "
"<%s id=0x%x len=%d",
SPP_ARGS(ifp),
sppp_auth_type_name(PPP_CHAP, h->type),
h->ident, ntohs(h->len));
sppp_print_bytes((u_char*)(h+1), len-4);
log(-1, ">\n");
}
break;
}
if (h->ident != sp->confid[IDX_CHAP]) {
if (debug)
log(LOG_DEBUG,
SPP_FMT "chap dropping response for old ID "
"(got %d, expected %d)\n",
SPP_ARGS(ifp),
h->ident, sp->confid[IDX_CHAP]);
break;
}
if (name_len != sppp_strnlen(sp->hisauth.name, AUTHNAMELEN)
|| bcmp(name, sp->hisauth.name, name_len) != 0) {
log(LOG_INFO, SPP_FMT "chap response, his name ",
SPP_ARGS(ifp));
sppp_print_string(name, name_len);
log(-1, " != expected ");
sppp_print_string(sp->hisauth.name,
sppp_strnlen(sp->hisauth.name, AUTHNAMELEN));
log(-1, "\n");
}
if (debug) {
log(LOG_DEBUG, SPP_FMT "chap input(%s) "
"<%s id=0x%x len=%d name=",
SPP_ARGS(ifp),
sppp_state_name(sp->state[IDX_CHAP]),
sppp_auth_type_name(PPP_CHAP, h->type),
h->ident, ntohs (h->len));
sppp_print_string((char*)name, name_len);
log(-1, " value-size=%d value=", value_len);
sppp_print_bytes(value, value_len);
log(-1, ">\n");
}
if (value_len != AUTHKEYLEN) {
if (debug)
log(LOG_DEBUG,
SPP_FMT "chap bad hash value length: "
"%d bytes, should be %d\n",
SPP_ARGS(ifp), value_len,
AUTHKEYLEN);
break;
}
MD5Init(&ctx);
MD5Update(&ctx, &h->ident, 1);
MD5Update(&ctx, sp->hisauth.secret,
sppp_strnlen(sp->hisauth.secret, AUTHKEYLEN));
MD5Update(&ctx, sp->myauth.challenge, AUTHKEYLEN);
MD5Final(digest, &ctx);
#define FAILMSG "Failed..."
#define SUCCMSG "Welcome!"
if (value_len != sizeof digest ||
bcmp(digest, value, value_len) != 0) {
/* action scn, tld */
sppp_auth_send(&chap, sp, CHAP_FAILURE, h->ident,
sizeof(FAILMSG) - 1, (u_char *)FAILMSG,
0);
chap.tld(sp);
break;
}
/* action sca, perhaps tlu */
if (sp->state[IDX_CHAP] == STATE_REQ_SENT ||
sp->state[IDX_CHAP] == STATE_OPENED)
sppp_auth_send(&chap, sp, CHAP_SUCCESS, h->ident,
sizeof(SUCCMSG) - 1, (u_char *)SUCCMSG,
0);
if (sp->state[IDX_CHAP] == STATE_REQ_SENT) {
sppp_cp_change_state(&chap, sp, STATE_OPENED);
chap.tlu(sp);
}
break;
default:
/* Unknown CHAP packet type -- ignore. */
if (debug) {
log(LOG_DEBUG, SPP_FMT "chap unknown input(%s) "
"<0x%x id=0x%xh len=%d",
SPP_ARGS(ifp),
sppp_state_name(sp->state[IDX_CHAP]),
h->type, h->ident, ntohs(h->len));
sppp_print_bytes((u_char*)(h+1), len-4);
log(-1, ">\n");
}
break;
}
}
static void
sppp_chap_init(struct sppp *sp)
{
/* Chap doesn't have STATE_INITIAL at all. */
sp->state[IDX_CHAP] = STATE_CLOSED;
sp->fail_counter[IDX_CHAP] = 0;
sp->pp_seq[IDX_CHAP] = 0;
sp->pp_rseq[IDX_CHAP] = 0;
callout_init(&sp->ch[IDX_CHAP], 1);
}
static void
sppp_chap_open(struct sppp *sp)
{
if (sp->myauth.proto == PPP_CHAP &&
(sp->lcp.opts & (1 << LCP_OPT_AUTH_PROTO)) != 0) {
/* we are authenticator for CHAP, start it */
chap.scr(sp);
sp->rst_counter[IDX_CHAP] = sp->lcp.max_configure;
sppp_cp_change_state(&chap, sp, STATE_REQ_SENT);
}
/* nothing to be done if we are peer, await a challenge */
}
static void
sppp_chap_close(struct sppp *sp)
{
if (sp->state[IDX_CHAP] != STATE_CLOSED)
sppp_cp_change_state(&chap, sp, STATE_CLOSED);
}
static void
sppp_chap_TO(void *cookie)
{
struct sppp *sp = (struct sppp *)cookie;
STDDCL;
SPPP_LOCK(sp);
if (debug)
log(LOG_DEBUG, SPP_FMT "chap TO(%s) rst_counter = %d\n",
SPP_ARGS(ifp),
sppp_state_name(sp->state[IDX_CHAP]),
sp->rst_counter[IDX_CHAP]);
if (--sp->rst_counter[IDX_CHAP] < 0)
/* TO- event */
switch (sp->state[IDX_CHAP]) {
case STATE_REQ_SENT:
chap.tld(sp);
sppp_cp_change_state(&chap, sp, STATE_CLOSED);
break;
}
else
/* TO+ (or TO*) event */
switch (sp->state[IDX_CHAP]) {
case STATE_OPENED:
/* TO* event */
sp->rst_counter[IDX_CHAP] = sp->lcp.max_configure;
/* FALLTHROUGH */
case STATE_REQ_SENT:
chap.scr(sp);
/* sppp_cp_change_state() will restart the timer */
sppp_cp_change_state(&chap, sp, STATE_REQ_SENT);
break;
}
SPPP_UNLOCK(sp);
}
static void
sppp_chap_tlu(struct sppp *sp)
{
STDDCL;
int i;
i = 0;
sp->rst_counter[IDX_CHAP] = sp->lcp.max_configure;
/*
* Some broken CHAP implementations (Conware CoNet, firmware
* 4.0.?) don't want to re-authenticate their CHAP once the
* initial challenge-response exchange has taken place.
* Provide for an option to avoid rechallenges.
*/
if ((sp->hisauth.flags & AUTHFLAG_NORECHALLENGE) == 0) {
/*
* Compute the re-challenge timeout. This will yield
* a number between 300 and 810 seconds.
*/
i = 300 + ((unsigned)(random() & 0xff00) >> 7);
callout_reset(&sp->ch[IDX_CHAP], i * hz, chap.TO, (void *)sp);
}
if (debug) {
log(LOG_DEBUG,
SPP_FMT "chap %s, ",
SPP_ARGS(ifp),
sp->pp_phase == PHASE_NETWORK? "reconfirmed": "tlu");
if ((sp->hisauth.flags & AUTHFLAG_NORECHALLENGE) == 0)
log(-1, "next re-challenge in %d seconds\n", i);
else
log(-1, "re-challenging suppressed\n");
}
SPPP_LOCK(sp);
/* indicate to LCP that we need to be closed down */
sp->lcp.protos |= (1 << IDX_CHAP);
if (sp->pp_flags & PP_NEEDAUTH) {
/*
* Remote is authenticator, but his auth proto didn't
* complete yet. Defer the transition to network
* phase.
*/
SPPP_UNLOCK(sp);
return;
}
SPPP_UNLOCK(sp);
/*
* If we are already in phase network, we are done here. This
* is the case if this is a dummy tlu event after a re-challenge.
*/
if (sp->pp_phase != PHASE_NETWORK)
sppp_phase_network(sp);
}
static void
sppp_chap_tld(struct sppp *sp)
{
STDDCL;
if (debug)
log(LOG_DEBUG, SPP_FMT "chap tld\n", SPP_ARGS(ifp));
callout_stop(&sp->ch[IDX_CHAP]);
sp->lcp.protos &= ~(1 << IDX_CHAP);
lcp.Close(sp);
}
static void
sppp_chap_scr(struct sppp *sp)
{
u_long *ch;
u_char clen;
/* Compute random challenge. */
ch = (u_long *)sp->myauth.challenge;
arc4random_buf(ch, 4 * sizeof(*ch));
clen = AUTHKEYLEN;
sp->confid[IDX_CHAP] = ++sp->pp_seq[IDX_CHAP];
sppp_auth_send(&chap, sp, CHAP_CHALLENGE, sp->confid[IDX_CHAP],
sizeof clen, (const char *)&clen,
(size_t)AUTHKEYLEN, sp->myauth.challenge,
(size_t)sppp_strnlen(sp->myauth.name, AUTHNAMELEN),
sp->myauth.name,
0);
}
/*
*--------------------------------------------------------------------------*
* *
* The PAP implementation. *
* *
*--------------------------------------------------------------------------*
*/
/*
* For PAP, we need to keep a little state also if we are the peer, not the
* authenticator. This is since we don't get a request to authenticate, but
* have to repeatedly authenticate ourself until we got a response (or the
* retry counter is expired).
*/
/*
* Handle incoming PAP packets. */
static void
sppp_pap_input(struct sppp *sp, struct mbuf *m)
{
STDDCL;
struct lcp_header *h;
int len;
u_char *name, *passwd, mlen;
int name_len, passwd_len;
len = m->m_pkthdr.len;
if (len < 5) {
if (debug)
log(LOG_DEBUG,
SPP_FMT "pap invalid packet length: %d bytes\n",
SPP_ARGS(ifp), len);
return;
}
h = mtod (m, struct lcp_header*);
if (len > ntohs (h->len))
len = ntohs (h->len);
switch (h->type) {
/* PAP request is my authproto */
case PAP_REQ:
name = 1 + (u_char*)(h+1);
name_len = name[-1];
passwd = name + name_len + 1;
if (name_len > len - 6 ||
(passwd_len = passwd[-1]) > len - 6 - name_len) {
if (debug) {
log(LOG_DEBUG, SPP_FMT "pap corrupted input "
"<%s id=0x%x len=%d",
SPP_ARGS(ifp),
sppp_auth_type_name(PPP_PAP, h->type),
h->ident, ntohs(h->len));
sppp_print_bytes((u_char*)(h+1), len-4);
log(-1, ">\n");
}
break;
}
if (debug) {
log(LOG_DEBUG, SPP_FMT "pap input(%s) "
"<%s id=0x%x len=%d name=",
SPP_ARGS(ifp),
sppp_state_name(sp->state[IDX_PAP]),
sppp_auth_type_name(PPP_PAP, h->type),
h->ident, ntohs(h->len));
sppp_print_string((char*)name, name_len);
log(-1, " passwd=");
sppp_print_string((char*)passwd, passwd_len);
log(-1, ">\n");
}
if (name_len != sppp_strnlen(sp->hisauth.name, AUTHNAMELEN) ||
passwd_len != sppp_strnlen(sp->hisauth.secret, AUTHKEYLEN) ||
bcmp(name, sp->hisauth.name, name_len) != 0 ||
bcmp(passwd, sp->hisauth.secret, passwd_len) != 0) {
/* action scn, tld */
mlen = sizeof(FAILMSG) - 1;
sppp_auth_send(&pap, sp, PAP_NAK, h->ident,
sizeof mlen, (const char *)&mlen,
sizeof(FAILMSG) - 1, (u_char *)FAILMSG,
0);
pap.tld(sp);
break;
}
/* action sca, perhaps tlu */
if (sp->state[IDX_PAP] == STATE_REQ_SENT ||
sp->state[IDX_PAP] == STATE_OPENED) {
mlen = sizeof(SUCCMSG) - 1;
sppp_auth_send(&pap, sp, PAP_ACK, h->ident,
sizeof mlen, (const char *)&mlen,
sizeof(SUCCMSG) - 1, (u_char *)SUCCMSG,
0);
}
if (sp->state[IDX_PAP] == STATE_REQ_SENT) {
sppp_cp_change_state(&pap, sp, STATE_OPENED);
pap.tlu(sp);
}
break;
/* ack and nak are his authproto */
case PAP_ACK:
callout_stop(&sp->pap_my_to_ch);
if (debug) {
log(LOG_DEBUG, SPP_FMT "pap success",
SPP_ARGS(ifp));
name_len = *((char *)h);
if (len > 5 && name_len) {
log(-1, ": ");
sppp_print_string((char*)(h+1), name_len);
}
log(-1, "\n");
}
SPPP_LOCK(sp);
sp->pp_flags &= ~PP_NEEDAUTH;
if (sp->myauth.proto == PPP_PAP &&
(sp->lcp.opts & (1 << LCP_OPT_AUTH_PROTO)) &&
(sp->lcp.protos & (1 << IDX_PAP)) == 0) {
/*
* We are authenticator for PAP but didn't
* complete yet. Leave it to tlu to proceed
* to network phase.
*/
SPPP_UNLOCK(sp);
break;
}
SPPP_UNLOCK(sp);
sppp_phase_network(sp);
break;
case PAP_NAK:
callout_stop (&sp->pap_my_to_ch);
if (debug) {
log(LOG_INFO, SPP_FMT "pap failure",
SPP_ARGS(ifp));
name_len = *((char *)h);
if (len > 5 && name_len) {
log(-1, ": ");
sppp_print_string((char*)(h+1), name_len);
}
log(-1, "\n");
} else
log(LOG_INFO, SPP_FMT "pap failure\n",
SPP_ARGS(ifp));
/* await LCP shutdown by authenticator */
break;
default:
/* Unknown PAP packet type -- ignore. */
if (debug) {
log(LOG_DEBUG, SPP_FMT "pap corrupted input "
"<0x%x id=0x%x len=%d",
SPP_ARGS(ifp),
h->type, h->ident, ntohs(h->len));
sppp_print_bytes((u_char*)(h+1), len-4);
log(-1, ">\n");
}
break;
}
}
static void
sppp_pap_init(struct sppp *sp)
{
/* PAP doesn't have STATE_INITIAL at all. */
sp->state[IDX_PAP] = STATE_CLOSED;
sp->fail_counter[IDX_PAP] = 0;
sp->pp_seq[IDX_PAP] = 0;
sp->pp_rseq[IDX_PAP] = 0;
callout_init(&sp->ch[IDX_PAP], 1);
callout_init(&sp->pap_my_to_ch, 1);
}
static void
sppp_pap_open(struct sppp *sp)
{
if (sp->hisauth.proto == PPP_PAP &&
(sp->lcp.opts & (1 << LCP_OPT_AUTH_PROTO)) != 0) {
/* we are authenticator for PAP, start our timer */
sp->rst_counter[IDX_PAP] = sp->lcp.max_configure;
sppp_cp_change_state(&pap, sp, STATE_REQ_SENT);
}
if (sp->myauth.proto == PPP_PAP) {
/* we are peer, send a request, and start a timer */
pap.scr(sp);
callout_reset(&sp->pap_my_to_ch, sp->lcp.timeout,
sppp_pap_my_TO, (void *)sp);
}
}
static void
sppp_pap_close(struct sppp *sp)
{
if (sp->state[IDX_PAP] != STATE_CLOSED)
sppp_cp_change_state(&pap, sp, STATE_CLOSED);
}
/*
* That's the timeout routine if we are authenticator. Since the
* authenticator is basically passive in PAP, we can't do much here.
*/
static void
sppp_pap_TO(void *cookie)
{
struct sppp *sp = (struct sppp *)cookie;
STDDCL;
SPPP_LOCK(sp);
if (debug)
log(LOG_DEBUG, SPP_FMT "pap TO(%s) rst_counter = %d\n",
SPP_ARGS(ifp),
sppp_state_name(sp->state[IDX_PAP]),
sp->rst_counter[IDX_PAP]);
if (--sp->rst_counter[IDX_PAP] < 0)
/* TO- event */
switch (sp->state[IDX_PAP]) {
case STATE_REQ_SENT:
pap.tld(sp);
sppp_cp_change_state(&pap, sp, STATE_CLOSED);
break;
}
else
/* TO+ event, not very much we could do */
switch (sp->state[IDX_PAP]) {
case STATE_REQ_SENT:
/* sppp_cp_change_state() will restart the timer */
sppp_cp_change_state(&pap, sp, STATE_REQ_SENT);
break;
}
SPPP_UNLOCK(sp);
}
/*
* That's the timeout handler if we are peer. Since the peer is active,
* we need to retransmit our PAP request since it is apparently lost.
* XXX We should impose a max counter.
*/
static void
sppp_pap_my_TO(void *cookie)
{
struct sppp *sp = (struct sppp *)cookie;
STDDCL;
if (debug)
log(LOG_DEBUG, SPP_FMT "pap peer TO\n",
SPP_ARGS(ifp));
SPPP_LOCK(sp);
pap.scr(sp);
SPPP_UNLOCK(sp);
}
static void
sppp_pap_tlu(struct sppp *sp)
{
STDDCL;
sp->rst_counter[IDX_PAP] = sp->lcp.max_configure;
if (debug)
log(LOG_DEBUG, SPP_FMT "%s tlu\n",
SPP_ARGS(ifp), pap.name);
SPPP_LOCK(sp);
/* indicate to LCP that we need to be closed down */
sp->lcp.protos |= (1 << IDX_PAP);
if (sp->pp_flags & PP_NEEDAUTH) {
/*
* Remote is authenticator, but his auth proto didn't
* complete yet. Defer the transition to network
* phase.
*/
SPPP_UNLOCK(sp);
return;
}
SPPP_UNLOCK(sp);
sppp_phase_network(sp);
}
static void
sppp_pap_tld(struct sppp *sp)
{
STDDCL;
if (debug)
log(LOG_DEBUG, SPP_FMT "pap tld\n", SPP_ARGS(ifp));
callout_stop (&sp->ch[IDX_PAP]);
callout_stop (&sp->pap_my_to_ch);
sp->lcp.protos &= ~(1 << IDX_PAP);
lcp.Close(sp);
}
static void
sppp_pap_scr(struct sppp *sp)
{
u_char idlen, pwdlen;
sp->confid[IDX_PAP] = ++sp->pp_seq[IDX_PAP];
pwdlen = sppp_strnlen(sp->myauth.secret, AUTHKEYLEN);
idlen = sppp_strnlen(sp->myauth.name, AUTHNAMELEN);
sppp_auth_send(&pap, sp, PAP_REQ, sp->confid[IDX_PAP],
sizeof idlen, (const char *)&idlen,
(size_t)idlen, sp->myauth.name,
sizeof pwdlen, (const char *)&pwdlen,
(size_t)pwdlen, sp->myauth.secret,
0);
}
/*
* Random miscellaneous functions.
*/
/*
* Send a PAP or CHAP proto packet.
*
* Varadic function, each of the elements for the ellipsis is of type
* ``size_t mlen, const u_char *msg''. Processing will stop iff
* mlen == 0.
* NOTE: never declare variadic functions with types subject to type
* promotion (i.e. u_char). This is asking for big trouble depending
* on the architecture you are on...
*/
static void
sppp_auth_send(const struct cp *cp, struct sppp *sp,
unsigned int type, unsigned int id,
...)
{
STDDCL;
struct ppp_header *h;
struct lcp_header *lh;
struct mbuf *m;
u_char *p;
int len;
unsigned int mlen;
const char *msg;
va_list ap;
MGETHDR (m, M_NOWAIT, MT_DATA);
if (! m)
return;
m->m_pkthdr.rcvif = 0;
h = mtod (m, struct ppp_header*);
h->address = PPP_ALLSTATIONS; /* broadcast address */
h->control = PPP_UI; /* Unnumbered Info */
h->protocol = htons(cp->proto);
lh = (struct lcp_header*)(h + 1);
lh->type = type;
lh->ident = id;
p = (u_char*) (lh+1);
va_start(ap, id);
len = 0;
while ((mlen = (unsigned int)va_arg(ap, size_t)) != 0) {
msg = va_arg(ap, const char *);
len += mlen;
if (len > MHLEN - PPP_HEADER_LEN - LCP_HEADER_LEN) {
va_end(ap);
m_freem(m);
return;
}
bcopy(msg, p, mlen);
p += mlen;
}
va_end(ap);
m->m_pkthdr.len = m->m_len = PPP_HEADER_LEN + LCP_HEADER_LEN + len;
lh->len = htons (LCP_HEADER_LEN + len);
if (debug) {
log(LOG_DEBUG, SPP_FMT "%s output <%s id=0x%x len=%d",
SPP_ARGS(ifp), cp->name,
sppp_auth_type_name(cp->proto, lh->type),
lh->ident, ntohs(lh->len));
sppp_print_bytes((u_char*) (lh+1), len);
log(-1, ">\n");
}
if (! IF_HANDOFF_ADJ(&sp->pp_cpq, m, ifp, 3))
if_inc_counter(ifp, IFCOUNTER_OERRORS, 1);
}
/*
* Flush interface queue.
*/
static void
sppp_qflush(struct ifqueue *ifq)
{
struct mbuf *m, *n;
n = ifq->ifq_head;
while ((m = n)) {
n = m->m_nextpkt;
m_freem (m);
}
ifq->ifq_head = 0;
ifq->ifq_tail = 0;
ifq->ifq_len = 0;
}
/*
* Send keepalive packets, every 10 seconds.
*/
static void
sppp_keepalive(void *dummy)
{
struct sppp *sp = (struct sppp*)dummy;
struct ifnet *ifp = SP2IFP(sp);
SPPP_LOCK(sp);
/* Keepalive mode disabled or channel down? */
if (! (sp->pp_flags & PP_KEEPALIVE) ||
! (ifp->if_drv_flags & IFF_DRV_RUNNING))
goto out;
if (sp->pp_mode == PP_FR) {
sppp_fr_keepalive (sp);
goto out;
}
/* No keepalive in PPP mode if LCP not opened yet. */
if (sp->pp_mode != IFF_CISCO &&
sp->pp_phase < PHASE_AUTHENTICATE)
goto out;
if (sp->pp_alivecnt == MAXALIVECNT) {
/* No keepalive packets got. Stop the interface. */
printf (SPP_FMT "down\n", SPP_ARGS(ifp));
if_down (ifp);
sppp_qflush (&sp->pp_cpq);
if (sp->pp_mode != IFF_CISCO) {
/* XXX */
/* Shut down the PPP link. */
lcp.Down(sp);
/* Initiate negotiation. XXX */
lcp.Up(sp);
}
}
if (sp->pp_alivecnt <= MAXALIVECNT)
++sp->pp_alivecnt;
if (sp->pp_mode == IFF_CISCO)
sppp_cisco_send (sp, CISCO_KEEPALIVE_REQ,
++sp->pp_seq[IDX_LCP], sp->pp_rseq[IDX_LCP]);
else if (sp->pp_phase >= PHASE_AUTHENTICATE) {
uint32_t nmagic = htonl(sp->lcp.magic);
sp->lcp.echoid = ++sp->pp_seq[IDX_LCP];
sppp_cp_send (sp, PPP_LCP, ECHO_REQ,
sp->lcp.echoid, 4, &nmagic);
}
out:
SPPP_UNLOCK(sp);
callout_reset(&sp->keepalive_callout, hz * 10, sppp_keepalive,
(void *)sp);
}
/*
* Get both IP addresses.
*/
void
sppp_get_ip_addrs(struct sppp *sp, u_long *src, u_long *dst, u_long *srcmask)
{
struct epoch_tracker et;
struct ifnet *ifp = SP2IFP(sp);
struct ifaddr *ifa;
struct sockaddr_in *si, *sm;
u_long ssrc, ddst;
sm = NULL;
ssrc = ddst = 0L;
/*
* Pick the first AF_INET address from the list,
* aliases don't make any sense on a p2p link anyway.
*/
si = NULL;
NET_EPOCH_ENTER(et);
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link)
if (ifa->ifa_addr->sa_family == AF_INET) {
si = (struct sockaddr_in *)ifa->ifa_addr;
sm = (struct sockaddr_in *)ifa->ifa_netmask;
if (si)
break;
}
if (ifa) {
if (si && si->sin_addr.s_addr) {
ssrc = si->sin_addr.s_addr;
if (srcmask)
*srcmask = ntohl(sm->sin_addr.s_addr);
}
si = (struct sockaddr_in *)ifa->ifa_dstaddr;
if (si && si->sin_addr.s_addr)
ddst = si->sin_addr.s_addr;
}
NET_EPOCH_EXIT(et);
if (dst) *dst = ntohl(ddst);
if (src) *src = ntohl(ssrc);
}
#ifdef INET
/*
* Set my IP address.
*/
static void
sppp_set_ip_addr(struct sppp *sp, u_long src)
{
STDDCL;
struct epoch_tracker et;
struct ifaddr *ifa;
struct sockaddr_in *si;
struct in_ifaddr *ia;
/*
* Pick the first AF_INET address from the list,
* aliases don't make any sense on a p2p link anyway.
*/
si = NULL;
NET_EPOCH_ENTER(et);
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family == AF_INET) {
si = (struct sockaddr_in *)ifa->ifa_addr;
if (si != NULL) {
ifa_ref(ifa);
break;
}
}
}
NET_EPOCH_EXIT(et);
if (ifa != NULL) {
int error;
+ int fibnum = ifp->if_fib;
+ rt_addrmsg(RTM_DELETE, ifa, fibnum);
/* delete old route */
- error = rtinit(ifa, (int)RTM_DELETE, RTF_HOST);
+ ia = ifatoia(ifa);
+ error = in_handle_ifaddr_route(RTM_DELETE, ia);
if (debug && error) {
log(LOG_DEBUG, SPP_FMT "sppp_set_ip_addr: rtinit DEL failed, error=%d\n",
SPP_ARGS(ifp), error);
}
/* set new address */
si->sin_addr.s_addr = htonl(src);
- ia = ifatoia(ifa);
IN_IFADDR_WLOCK();
LIST_REMOVE(ia, ia_hash);
LIST_INSERT_HEAD(INADDR_HASH(si->sin_addr.s_addr), ia, ia_hash);
IN_IFADDR_WUNLOCK();
+ rt_addrmsg(RTM_ADD, ifa, fibnum);
/* add new route */
- error = rtinit(ifa, (int)RTM_ADD, RTF_HOST);
+ error = in_handle_ifaddr_route(RTM_ADD, ia);
if (debug && error) {
log(LOG_DEBUG, SPP_FMT "sppp_set_ip_addr: rtinit ADD failed, error=%d",
SPP_ARGS(ifp), error);
}
ifa_free(ifa);
}
}
#endif
#ifdef INET6
/*
* Get both IPv6 addresses.
*/
static void
sppp_get_ip6_addrs(struct sppp *sp, struct in6_addr *src, struct in6_addr *dst,
struct in6_addr *srcmask)
{
struct epoch_tracker et;
struct ifnet *ifp = SP2IFP(sp);
struct ifaddr *ifa;
struct sockaddr_in6 *si, *sm;
struct in6_addr ssrc, ddst;
sm = NULL;
bzero(&ssrc, sizeof(ssrc));
bzero(&ddst, sizeof(ddst));
/*
* Pick the first link-local AF_INET6 address from the list,
* aliases don't make any sense on a p2p link anyway.
*/
si = NULL;
NET_EPOCH_ENTER(et);
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link)
if (ifa->ifa_addr->sa_family == AF_INET6) {
si = (struct sockaddr_in6 *)ifa->ifa_addr;
sm = (struct sockaddr_in6 *)ifa->ifa_netmask;
if (si && IN6_IS_ADDR_LINKLOCAL(&si->sin6_addr))
break;
}
if (ifa) {
if (si && !IN6_IS_ADDR_UNSPECIFIED(&si->sin6_addr)) {
bcopy(&si->sin6_addr, &ssrc, sizeof(ssrc));
if (srcmask) {
bcopy(&sm->sin6_addr, srcmask,
sizeof(*srcmask));
}
}
si = (struct sockaddr_in6 *)ifa->ifa_dstaddr;
if (si && !IN6_IS_ADDR_UNSPECIFIED(&si->sin6_addr))
bcopy(&si->sin6_addr, &ddst, sizeof(ddst));
}
if (dst)
bcopy(&ddst, dst, sizeof(*dst));
if (src)
bcopy(&ssrc, src, sizeof(*src));
NET_EPOCH_EXIT(et);
}
#ifdef IPV6CP_MYIFID_DYN
/*
* Generate random ifid.
*/
static void
sppp_gen_ip6_addr(struct sppp *sp, struct in6_addr *addr)
{
/* TBD */
}
/*
* Set my IPv6 address.
*/
static void
sppp_set_ip6_addr(struct sppp *sp, const struct in6_addr *src)
{
STDDCL;
struct epoch_tracker et;
struct ifaddr *ifa;
struct sockaddr_in6 *sin6;
/*
* Pick the first link-local AF_INET6 address from the list,
* aliases don't make any sense on a p2p link anyway.
*/
sin6 = NULL;
NET_EPOCH_ENTER(et);
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family == AF_INET6) {
sin6 = (struct sockaddr_in6 *)ifa->ifa_addr;
if (sin6 && IN6_IS_ADDR_LINKLOCAL(&sin6->sin6_addr)) {
ifa_ref(ifa);
break;
}
}
}
NET_EPOCH_EXIT(et);
if (ifa != NULL) {
int error;
struct sockaddr_in6 new_sin6 = *sin6;
bcopy(src, &new_sin6.sin6_addr, sizeof(new_sin6.sin6_addr));
error = in6_ifinit(ifp, ifatoia6(ifa), &new_sin6, 1);
if (debug && error) {
log(LOG_DEBUG, SPP_FMT "sppp_set_ip6_addr: in6_ifinit "
" failed, error=%d\n", SPP_ARGS(ifp), error);
}
ifa_free(ifa);
}
}
#endif
/*
* Suggest a candidate address to be used by peer.
*/
static void
sppp_suggest_ip6_addr(struct sppp *sp, struct in6_addr *suggest)
{
struct in6_addr myaddr;
struct timeval tv;
sppp_get_ip6_addrs(sp, &myaddr, 0, 0);
myaddr.s6_addr[8] &= ~0x02; /* u bit to "local" */
microtime(&tv);
if ((tv.tv_usec & 0xff) == 0 && (tv.tv_sec & 0xff) == 0) {
myaddr.s6_addr[14] ^= 0xff;
myaddr.s6_addr[15] ^= 0xff;
} else {
myaddr.s6_addr[14] ^= (tv.tv_usec & 0xff);
myaddr.s6_addr[15] ^= (tv.tv_sec & 0xff);
}
if (suggest)
bcopy(&myaddr, suggest, sizeof(myaddr));
}
#endif /*INET6*/
static int
sppp_params(struct sppp *sp, u_long cmd, void *data)
{
u_long subcmd;
struct ifreq *ifr = (struct ifreq *)data;
struct spppreq *spr;
int rv = 0;
if ((spr = malloc(sizeof(struct spppreq), M_TEMP, M_NOWAIT)) == NULL)
return (EAGAIN);
/*
* ifr_data_get_ptr(ifr) is supposed to point to a struct spppreq.
* Check the cmd word first before attempting to fetch all the
* data.
*/
rv = fueword(ifr_data_get_ptr(ifr), &subcmd);
if (rv == -1) {
rv = EFAULT;
goto quit;
}
if (copyin(ifr_data_get_ptr(ifr), spr, sizeof(struct spppreq)) != 0) {
rv = EFAULT;
goto quit;
}
switch (subcmd) {
case (u_long)SPPPIOGDEFS:
if (cmd != SIOCGIFGENERIC) {
rv = EINVAL;
break;
}
/*
* We copy over the entire current state, but clean
* out some of the stuff we don't wanna pass up.
* Remember, SIOCGIFGENERIC is unprotected, and can be
* called by any user. No need to ever get PAP or
* CHAP secrets back to userland anyway.
*/
spr->defs.pp_phase = sp->pp_phase;
spr->defs.enable_vj = (sp->confflags & CONF_ENABLE_VJ) != 0;
spr->defs.enable_ipv6 = (sp->confflags & CONF_ENABLE_IPV6) != 0;
spr->defs.lcp = sp->lcp;
spr->defs.ipcp = sp->ipcp;
spr->defs.ipv6cp = sp->ipv6cp;
spr->defs.myauth = sp->myauth;
spr->defs.hisauth = sp->hisauth;
bzero(spr->defs.myauth.secret, AUTHKEYLEN);
bzero(spr->defs.myauth.challenge, AUTHKEYLEN);
bzero(spr->defs.hisauth.secret, AUTHKEYLEN);
bzero(spr->defs.hisauth.challenge, AUTHKEYLEN);
/*
* Fixup the LCP timeout value to milliseconds so
* spppcontrol doesn't need to bother about the value
* of "hz". We do the reverse calculation below when
* setting it.
*/
spr->defs.lcp.timeout = sp->lcp.timeout * 1000 / hz;
rv = copyout(spr, ifr_data_get_ptr(ifr),
sizeof(struct spppreq));
break;
case (u_long)SPPPIOSDEFS:
if (cmd != SIOCSIFGENERIC) {
rv = EINVAL;
break;
}
/*
* We have a very specific idea of which fields we
* allow being passed back from userland, so to not
* clobber our current state. For one, we only allow
* setting anything if LCP is in dead or establish
* phase. Once the authentication negotiations
* started, the authentication settings must not be
* changed again. (The administrator can force an
* ifconfig down in order to get LCP back into dead
* phase.)
*
* Also, we only allow for authentication parameters to be
* specified.
*
* XXX Should allow to set or clear pp_flags.
*
* Finally, if the respective authentication protocol to
* be used is set differently than 0, but the secret is
* passed as all zeros, we don't trash the existing secret.
* This allows an administrator to change the system name
* only without clobbering the secret (which he didn't get
* back in a previous SPPPIOGDEFS call). However, the
* secrets are cleared if the authentication protocol is
* reset to 0. */
if (sp->pp_phase != PHASE_DEAD &&
sp->pp_phase != PHASE_ESTABLISH) {
rv = EBUSY;
break;
}
if ((spr->defs.myauth.proto != 0 && spr->defs.myauth.proto != PPP_PAP &&
spr->defs.myauth.proto != PPP_CHAP) ||
(spr->defs.hisauth.proto != 0 && spr->defs.hisauth.proto != PPP_PAP &&
spr->defs.hisauth.proto != PPP_CHAP)) {
rv = EINVAL;
break;
}
if (spr->defs.myauth.proto == 0)
/* resetting myauth */
bzero(&sp->myauth, sizeof sp->myauth);
else {
/* setting/changing myauth */
sp->myauth.proto = spr->defs.myauth.proto;
bcopy(spr->defs.myauth.name, sp->myauth.name, AUTHNAMELEN);
if (spr->defs.myauth.secret[0] != '\0')
bcopy(spr->defs.myauth.secret, sp->myauth.secret,
AUTHKEYLEN);
}
if (spr->defs.hisauth.proto == 0)
/* resetting hisauth */
bzero(&sp->hisauth, sizeof sp->hisauth);
else {
/* setting/changing hisauth */
sp->hisauth.proto = spr->defs.hisauth.proto;
sp->hisauth.flags = spr->defs.hisauth.flags;
bcopy(spr->defs.hisauth.name, sp->hisauth.name, AUTHNAMELEN);
if (spr->defs.hisauth.secret[0] != '\0')
bcopy(spr->defs.hisauth.secret, sp->hisauth.secret,
AUTHKEYLEN);
}
/* set LCP restart timer timeout */
if (spr->defs.lcp.timeout != 0)
sp->lcp.timeout = spr->defs.lcp.timeout * hz / 1000;
/* set VJ enable and IPv6 disable flags */
#ifdef INET
if (spr->defs.enable_vj)
sp->confflags |= CONF_ENABLE_VJ;
else
sp->confflags &= ~CONF_ENABLE_VJ;
#endif
#ifdef INET6
if (spr->defs.enable_ipv6)
sp->confflags |= CONF_ENABLE_IPV6;
else
sp->confflags &= ~CONF_ENABLE_IPV6;
#endif
break;
default:
rv = EINVAL;
}
quit:
free(spr, M_TEMP);
return (rv);
}
static void
sppp_phase_network(struct sppp *sp)
{
STDDCL;
int i;
u_long mask;
sp->pp_phase = PHASE_NETWORK;
if (debug)
log(LOG_DEBUG, SPP_FMT "phase %s\n", SPP_ARGS(ifp),
sppp_phase_name(sp->pp_phase));
/* Notify NCPs now. */
for (i = 0; i < IDX_COUNT; i++)
if ((cps[i])->flags & CP_NCP)
(cps[i])->Open(sp);
/* Send Up events to all NCPs. */
for (i = 0, mask = 1; i < IDX_COUNT; i++, mask <<= 1)
if ((sp->lcp.protos & mask) && ((cps[i])->flags & CP_NCP))
(cps[i])->Up(sp);
/* if no NCP is starting, all this was in vain, close down */
sppp_lcp_check_and_close(sp);
}
static const char *
sppp_cp_type_name(u_char type)
{
static char buf[12];
switch (type) {
case CONF_REQ: return "conf-req";
case CONF_ACK: return "conf-ack";
case CONF_NAK: return "conf-nak";
case CONF_REJ: return "conf-rej";
case TERM_REQ: return "term-req";
case TERM_ACK: return "term-ack";
case CODE_REJ: return "code-rej";
case PROTO_REJ: return "proto-rej";
case ECHO_REQ: return "echo-req";
case ECHO_REPLY: return "echo-reply";
case DISC_REQ: return "discard-req";
}
snprintf (buf, sizeof(buf), "cp/0x%x", type);
return buf;
}
static const char *
sppp_auth_type_name(u_short proto, u_char type)
{
static char buf[12];
switch (proto) {
case PPP_CHAP:
switch (type) {
case CHAP_CHALLENGE: return "challenge";
case CHAP_RESPONSE: return "response";
case CHAP_SUCCESS: return "success";
case CHAP_FAILURE: return "failure";
}
case PPP_PAP:
switch (type) {
case PAP_REQ: return "req";
case PAP_ACK: return "ack";
case PAP_NAK: return "nak";
}
}
snprintf (buf, sizeof(buf), "auth/0x%x", type);
return buf;
}
static const char *
sppp_lcp_opt_name(u_char opt)
{
static char buf[12];
switch (opt) {
case LCP_OPT_MRU: return "mru";
case LCP_OPT_ASYNC_MAP: return "async-map";
case LCP_OPT_AUTH_PROTO: return "auth-proto";
case LCP_OPT_QUAL_PROTO: return "qual-proto";
case LCP_OPT_MAGIC: return "magic";
case LCP_OPT_PROTO_COMP: return "proto-comp";
case LCP_OPT_ADDR_COMP: return "addr-comp";
}
snprintf (buf, sizeof(buf), "lcp/0x%x", opt);
return buf;
}
#ifdef INET
static const char *
sppp_ipcp_opt_name(u_char opt)
{
static char buf[12];
switch (opt) {
case IPCP_OPT_ADDRESSES: return "addresses";
case IPCP_OPT_COMPRESSION: return "compression";
case IPCP_OPT_ADDRESS: return "address";
}
snprintf (buf, sizeof(buf), "ipcp/0x%x", opt);
return buf;
}
#endif
#ifdef INET6
static const char *
sppp_ipv6cp_opt_name(u_char opt)
{
static char buf[12];
switch (opt) {
case IPV6CP_OPT_IFID: return "ifid";
case IPV6CP_OPT_COMPRESSION: return "compression";
}
sprintf (buf, "0x%x", opt);
return buf;
}
#endif
static const char *
sppp_state_name(int state)
{
switch (state) {
case STATE_INITIAL: return "initial";
case STATE_STARTING: return "starting";
case STATE_CLOSED: return "closed";
case STATE_STOPPED: return "stopped";
case STATE_CLOSING: return "closing";
case STATE_STOPPING: return "stopping";
case STATE_REQ_SENT: return "req-sent";
case STATE_ACK_RCVD: return "ack-rcvd";
case STATE_ACK_SENT: return "ack-sent";
case STATE_OPENED: return "opened";
}
return "illegal";
}
static const char *
sppp_phase_name(enum ppp_phase phase)
{
switch (phase) {
case PHASE_DEAD: return "dead";
case PHASE_ESTABLISH: return "establish";
case PHASE_TERMINATE: return "terminate";
case PHASE_AUTHENTICATE: return "authenticate";
case PHASE_NETWORK: return "network";
}
return "illegal";
}
static const char *
sppp_proto_name(u_short proto)
{
static char buf[12];
switch (proto) {
case PPP_LCP: return "lcp";
case PPP_IPCP: return "ipcp";
case PPP_PAP: return "pap";
case PPP_CHAP: return "chap";
case PPP_IPV6CP: return "ipv6cp";
}
snprintf(buf, sizeof(buf), "proto/0x%x", (unsigned)proto);
return buf;
}
static void
sppp_print_bytes(const u_char *p, u_short len)
{
if (len)
log(-1, " %*D", len, p, "-");
}
static void
sppp_print_string(const char *p, u_short len)
{
u_char c;
while (len-- > 0) {
c = *p++;
/*
* Print only ASCII chars directly. RFC 1994 recommends
* using only them, but we don't rely on it. */
if (c < ' ' || c > '~')
log(-1, "\\x%x", c);
else
log(-1, "%c", c);
}
}
#ifdef INET
static const char *
sppp_dotted_quad(u_long addr)
{
static char s[16];
sprintf(s, "%d.%d.%d.%d",
(int)((addr >> 24) & 0xff),
(int)((addr >> 16) & 0xff),
(int)((addr >> 8) & 0xff),
(int)(addr & 0xff));
return s;
}
#endif
static int
sppp_strnlen(u_char *p, int max)
{
int len;
for (len = 0; len < max && *p; ++p)
++len;
return len;
}
/* a dummy, used to drop uninteresting events */
static void
sppp_null(struct sppp *unused)
{
/* do just nothing */
}
diff --git a/sys/net/route.c b/sys/net/route.c
index b3383f90789b..7e087569d45f 100644
--- a/sys/net/route.c
+++ b/sys/net/route.c
@@ -1,793 +1,769 @@
/*-
* SPDX-License-Identifier: BSD-3-Clause
*
* Copyright (c) 1980, 1986, 1991, 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.
*
* @(#)route.c 8.3.1.1 (Berkeley) 2/23/95
* $FreeBSD$
*/
/************************************************************************
* Note: In this file a 'fib' is a "forwarding information base" *
* Which is the new name for an in kernel routing (next hop) table. *
***********************************************************************/
#include "opt_inet.h"
#include "opt_inet6.h"
#include "opt_mrouting.h"
#include "opt_route.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/socket.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>
#include <sys/sysproto.h>
#include <sys/proc.h>
#include <sys/domain.h>
#include <sys/eventhandler.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/rmlock.h>
#include <net/if.h>
#include <net/if_var.h>
#include <net/if_dl.h>
#include <net/route.h>
#include <net/route/route_ctl.h>
#include <net/route/route_var.h>
#include <net/route/nhop.h>
#include <net/vnet.h>
#include <netinet/in.h>
#include <netinet/ip_mroute.h>
VNET_PCPUSTAT_DEFINE(struct rtstat, rtstat);
VNET_PCPUSTAT_SYSINIT(rtstat);
#ifdef VIMAGE
VNET_PCPUSTAT_SYSUNINIT(rtstat);
#endif
EVENTHANDLER_LIST_DEFINE(rt_addrmsg);
static int rt_ifdelroute(const struct rtentry *rt, const struct nhop_object *,
void *arg);
static int rt_exportinfo(struct rtentry *rt, struct rt_addrinfo *info,
int flags);
/*
* route initialization must occur before ip6_init2(), which happenas at
* SI_ORDER_MIDDLE.
*/
static void
route_init(void)
{
nhops_init();
}
SYSINIT(route_init, SI_SUB_PROTO_DOMAIN, SI_ORDER_THIRD, route_init, NULL);
struct rib_head *
rt_table_init(int offset, int family, u_int fibnum)
{
struct rib_head *rh;
rh = malloc(sizeof(struct rib_head), M_RTABLE, M_WAITOK | M_ZERO);
/* TODO: These details should be hidded inside radix.c */
/* Init masks tree */
rn_inithead_internal(&rh->head, rh->rnh_nodes, offset);
rn_inithead_internal(&rh->rmhead.head, rh->rmhead.mask_nodes, 0);
rh->head.rnh_masks = &rh->rmhead;
/* Save metadata associated with this routing table. */
rh->rib_family = family;
rh->rib_fibnum = fibnum;
#ifdef VIMAGE
rh->rib_vnet = curvnet;
#endif
tmproutes_init(rh);
/* Init locks */
RIB_LOCK_INIT(rh);
nhops_init_rib(rh);
/* Init subscription system */
rib_init_subscriptions(rh);
/* Finally, set base callbacks */
rh->rnh_addaddr = rn_addroute;
rh->rnh_deladdr = rn_delete;
rh->rnh_matchaddr = rn_match;
rh->rnh_lookup = rn_lookup;
rh->rnh_walktree = rn_walktree;
rh->rnh_walktree_from = rn_walktree_from;
return (rh);
}
static int
rt_freeentry(struct radix_node *rn, void *arg)
{
struct radix_head * const rnh = arg;
struct radix_node *x;
x = (struct radix_node *)rn_delete(rn + 2, NULL, rnh);
if (x != NULL)
R_Free(x);
return (0);
}
void
rt_table_destroy(struct rib_head *rh)
{
RIB_WLOCK(rh);
rh->rib_dying = true;
RIB_WUNLOCK(rh);
#ifdef FIB_ALGO
fib_destroy_rib(rh);
#endif
tmproutes_destroy(rh);
rn_walktree(&rh->rmhead.head, rt_freeentry, &rh->rmhead.head);
nhops_destroy_rib(rh);
rib_destroy_subscriptions(rh);
/* Assume table is already empty */
RIB_LOCK_DESTROY(rh);
free(rh, M_RTABLE);
}
/*
* Adds a temporal redirect entry to the routing table.
* @fibnum: fib number
* @dst: destination to install redirect to
* @gateway: gateway to go via
* @author: sockaddr of originating router, can be NULL
* @ifp: interface to use for the redirected route
* @flags: set of flags to add. Allowed: RTF_GATEWAY
* @lifetime_sec: time in seconds to expire this redirect.
*
* Retuns 0 on success, errno otherwise.
*/
int
rib_add_redirect(u_int fibnum, struct sockaddr *dst, struct sockaddr *gateway,
struct sockaddr *author, struct ifnet *ifp, int flags, int lifetime_sec)
{
struct rib_cmd_info rc;
int error;
struct rt_addrinfo info;
struct rt_metrics rti_rmx;
struct ifaddr *ifa;
NET_EPOCH_ASSERT();
if (rt_tables_get_rnh(fibnum, dst->sa_family) == NULL)
return (EAFNOSUPPORT);
/* Verify the allowed flag mask. */
KASSERT(((flags & ~(RTF_GATEWAY)) == 0),
("invalid redirect flags: %x", flags));
flags |= RTF_HOST | RTF_DYNAMIC;
/* Get the best ifa for the given interface and gateway. */
if ((ifa = ifaof_ifpforaddr(gateway, ifp)) == NULL)
return (ENETUNREACH);
ifa_ref(ifa);
bzero(&info, sizeof(info));
info.rti_info[RTAX_DST] = dst;
info.rti_info[RTAX_GATEWAY] = gateway;
info.rti_ifa = ifa;
info.rti_ifp = ifp;
info.rti_flags = flags;
/* Setup route metrics to define expire time. */
bzero(&rti_rmx, sizeof(rti_rmx));
/* Set expire time as absolute. */
rti_rmx.rmx_expire = lifetime_sec + time_second;
info.rti_mflags |= RTV_EXPIRE;
info.rti_rmx = &rti_rmx;
error = rib_action(fibnum, RTM_ADD, &info, &rc);
ifa_free(ifa);
if (error != 0) {
/* TODO: add per-fib redirect stats. */
return (error);
}
RTSTAT_INC(rts_dynamic);
/* Send notification of a route addition to userland. */
bzero(&info, sizeof(info));
info.rti_info[RTAX_DST] = dst;
info.rti_info[RTAX_GATEWAY] = gateway;
info.rti_info[RTAX_AUTHOR] = author;
rt_missmsg_fib(RTM_REDIRECT, &info, flags | RTF_UP, error, fibnum);
return (0);
}
/*
* Routing table ioctl interface.
*/
int
rtioctl_fib(u_long req, caddr_t data, u_int fibnum)
{
/*
* If more ioctl commands are added here, make sure the proper
* super-user checks are being performed because it is possible for
* prison-root to make it this far if raw sockets have been enabled
* in jails.
*/
#ifdef INET
/* Multicast goop, grrr... */
return mrt_ioctl ? mrt_ioctl(req, data, fibnum) : EOPNOTSUPP;
#else /* INET */
return ENXIO;
#endif /* INET */
}
struct ifaddr *
ifa_ifwithroute(int flags, const struct sockaddr *dst,
const struct sockaddr *gateway, u_int fibnum)
{
struct ifaddr *ifa;
NET_EPOCH_ASSERT();
if ((flags & RTF_GATEWAY) == 0) {
/*
* If we are adding a route to an interface,
* and the interface is a pt to pt link
* we should search for the destination
* as our clue to the interface. Otherwise
* we can use the local address.
*/
ifa = NULL;
if (flags & RTF_HOST)
ifa = ifa_ifwithdstaddr(dst, fibnum);
if (ifa == NULL)
ifa = ifa_ifwithaddr(gateway);
} else {
/*
* If we are adding a route to a remote net
* or host, the gateway may still be on the
* other end of a pt to pt link.
*/
ifa = ifa_ifwithdstaddr(gateway, fibnum);
}
if (ifa == NULL)
ifa = ifa_ifwithnet(gateway, 0, fibnum);
if (ifa == NULL) {
struct nhop_object *nh;
nh = rib_lookup(fibnum, gateway, NHR_NONE, 0);
/*
* dismiss a gateway that is reachable only
* through the default router
*/
if ((nh == NULL) || (nh->nh_flags & NHF_DEFAULT))
return (NULL);
ifa = nh->nh_ifa;
}
if (ifa->ifa_addr->sa_family != dst->sa_family) {
struct ifaddr *oifa = ifa;
ifa = ifaof_ifpforaddr(dst, ifa->ifa_ifp);
if (ifa == NULL)
ifa = oifa;
}
return (ifa);
}
/*
* Copy most of @rt data into @info.
*
* If @flags contains NHR_COPY, copies dst,netmask and gw to the
* pointers specified by @info structure. Assume such pointers
* are zeroed sockaddr-like structures with sa_len field initialized
* to reflect size of the provided buffer. if no NHR_COPY is specified,
* point dst,netmask and gw @info fields to appropriate @rt values.
*
* if @flags contains NHR_REF, do refcouting on rt_ifp and rt_ifa.
*
* Returns 0 on success.
*/
int
rt_exportinfo(struct rtentry *rt, struct rt_addrinfo *info, int flags)
{
struct rt_metrics *rmx;
struct sockaddr *src, *dst;
struct nhop_object *nh;
int sa_len;
nh = rt->rt_nhop;
if (flags & NHR_COPY) {
/* Copy destination if dst is non-zero */
src = rt_key(rt);
dst = info->rti_info[RTAX_DST];
sa_len = src->sa_len;
if (dst != NULL) {
if (src->sa_len > dst->sa_len)
return (ENOMEM);
memcpy(dst, src, src->sa_len);
info->rti_addrs |= RTA_DST;
}
/* Copy mask if set && dst is non-zero */
src = rt_mask(rt);
dst = info->rti_info[RTAX_NETMASK];
if (src != NULL && dst != NULL) {
/*
* Radix stores different value in sa_len,
* assume rt_mask() to have the same length
* as rt_key()
*/
if (sa_len > dst->sa_len)
return (ENOMEM);
memcpy(dst, src, src->sa_len);
info->rti_addrs |= RTA_NETMASK;
}
/* Copy gateway is set && dst is non-zero */
src = &nh->gw_sa;
dst = info->rti_info[RTAX_GATEWAY];
if ((nhop_get_rtflags(nh) & RTF_GATEWAY) &&
src != NULL && dst != NULL) {
if (src->sa_len > dst->sa_len)
return (ENOMEM);
memcpy(dst, src, src->sa_len);
info->rti_addrs |= RTA_GATEWAY;
}
} else {
info->rti_info[RTAX_DST] = rt_key(rt);
info->rti_addrs |= RTA_DST;
if (rt_mask(rt) != NULL) {
info->rti_info[RTAX_NETMASK] = rt_mask(rt);
info->rti_addrs |= RTA_NETMASK;
}
if (nhop_get_rtflags(nh) & RTF_GATEWAY) {
info->rti_info[RTAX_GATEWAY] = &nh->gw_sa;
info->rti_addrs |= RTA_GATEWAY;
}
}
rmx = info->rti_rmx;
if (rmx != NULL) {
info->rti_mflags |= RTV_MTU;
rmx->rmx_mtu = nh->nh_mtu;
}
info->rti_flags = rt->rte_flags | nhop_get_rtflags(nh);
info->rti_ifp = nh->nh_ifp;
info->rti_ifa = nh->nh_ifa;
if (flags & NHR_REF) {
if_ref(info->rti_ifp);
ifa_ref(info->rti_ifa);
}
return (0);
}
/*
* Lookups up route entry for @dst in RIB database for fib @fibnum.
* Exports entry data to @info using rt_exportinfo().
*
* If @flags contains NHR_REF, refcouting is performed on rt_ifp and rt_ifa.
* All references can be released later by calling rib_free_info().
*
* Returns 0 on success.
* Returns ENOENT for lookup failure, ENOMEM for export failure.
*/
int
rib_lookup_info(uint32_t fibnum, const struct sockaddr *dst, uint32_t flags,
uint32_t flowid, struct rt_addrinfo *info)
{
RIB_RLOCK_TRACKER;
struct rib_head *rh;
struct radix_node *rn;
struct rtentry *rt;
int error;
KASSERT((fibnum < rt_numfibs), ("rib_lookup_rte: bad fibnum"));
rh = rt_tables_get_rnh(fibnum, dst->sa_family);
if (rh == NULL)
return (ENOENT);
RIB_RLOCK(rh);
rn = rh->rnh_matchaddr(__DECONST(void *, dst), &rh->head);
if (rn != NULL && ((rn->rn_flags & RNF_ROOT) == 0)) {
rt = RNTORT(rn);
/* Ensure route & ifp is UP */
if (RT_LINK_IS_UP(rt->rt_nhop->nh_ifp)) {
flags = (flags & NHR_REF) | NHR_COPY;
error = rt_exportinfo(rt, info, flags);
RIB_RUNLOCK(rh);
return (error);
}
}
RIB_RUNLOCK(rh);
return (ENOENT);
}
/*
* Releases all references acquired by rib_lookup_info() when
* called with NHR_REF flags.
*/
void
rib_free_info(struct rt_addrinfo *info)
{
ifa_free(info->rti_ifa);
if_rele(info->rti_ifp);
}
/*
* Delete Routes for a Network Interface
*
* Called for each routing entry via the rnh->rnh_walktree() call above
* to delete all route entries referencing a detaching network interface.
*
* Arguments:
* rt pointer to rtentry
* nh pointer to nhop
* arg argument passed to rnh->rnh_walktree() - detaching interface
*
* Returns:
* 0 successful
* errno failed - reason indicated
*/
static int
rt_ifdelroute(const struct rtentry *rt, const struct nhop_object *nh, void *arg)
{
struct ifnet *ifp = arg;
if (nh->nh_ifp != ifp)
return (0);
/*
* Protect (sorta) against walktree recursion problems
* with cloned routes
*/
if ((rt->rte_flags & RTF_UP) == 0)
return (0);
return (1);
}
/*
* Delete all remaining routes using this interface
* Unfortuneatly the only way to do this is to slog through
* the entire routing table looking for routes which point
* to this interface...oh well...
*/
void
rt_flushifroutes_af(struct ifnet *ifp, int af)
{
KASSERT((af >= 1 && af <= AF_MAX), ("%s: af %d not >= 1 and <= %d",
__func__, af, AF_MAX));
rib_foreach_table_walk_del(af, rt_ifdelroute, ifp);
}
void
rt_flushifroutes(struct ifnet *ifp)
{
rib_foreach_table_walk_del(AF_UNSPEC, rt_ifdelroute, ifp);
}
/*
* Look up rt_addrinfo for a specific fib. Note that if rti_ifa is defined,
* it will be referenced so the caller must free it.
*
* Assume basic consistency checks are executed by callers:
* RTAX_DST exists, if RTF_GATEWAY is set, RTAX_GATEWAY exists as well.
*/
int
rt_getifa_fib(struct rt_addrinfo *info, u_int fibnum)
{
const struct sockaddr *dst, *gateway, *ifpaddr, *ifaaddr;
struct epoch_tracker et;
int needref, error, flags;
dst = info->rti_info[RTAX_DST];
gateway = info->rti_info[RTAX_GATEWAY];
ifpaddr = info->rti_info[RTAX_IFP];
ifaaddr = info->rti_info[RTAX_IFA];
flags = info->rti_flags;
/*
* ifp may be specified by sockaddr_dl
* when protocol address is ambiguous.
*/
error = 0;
needref = (info->rti_ifa == NULL);
NET_EPOCH_ENTER(et);
/* If we have interface specified by the ifindex in the address, use it */
if (info->rti_ifp == NULL && ifpaddr != NULL &&
ifpaddr->sa_family == AF_LINK) {
const struct sockaddr_dl *sdl = (const struct sockaddr_dl *)ifpaddr;
if (sdl->sdl_index != 0)
info->rti_ifp = ifnet_byindex(sdl->sdl_index);
}
/*
* If we have source address specified, try to find it
* TODO: avoid enumerating all ifas on all interfaces.
*/
if (info->rti_ifa == NULL && ifaaddr != NULL)
info->rti_ifa = ifa_ifwithaddr(ifaaddr);
if (info->rti_ifa == NULL) {
const struct sockaddr *sa;
/*
* Most common use case for the userland-supplied routes.
*
* Choose sockaddr to select ifa.
* -- if ifp is set --
* Order of preference:
* 1) IFA address
* 2) gateway address
* Note: for interface routes link-level gateway address
* is specified to indicate the interface index without
* specifying RTF_GATEWAY. In this case, ignore gateway
* Note: gateway AF may be different from dst AF. In this case,
* ignore gateway
* 3) final destination.
* 4) if all of these fails, try to get at least link-level ifa.
* -- else --
* try to lookup gateway or dst in the routing table to get ifa
*/
if (info->rti_info[RTAX_IFA] != NULL)
sa = info->rti_info[RTAX_IFA];
else if ((info->rti_flags & RTF_GATEWAY) != 0 &&
gateway->sa_family == dst->sa_family)
sa = gateway;
else
sa = dst;
if (info->rti_ifp != NULL) {
info->rti_ifa = ifaof_ifpforaddr(sa, info->rti_ifp);
/* Case 4 */
if (info->rti_ifa == NULL && gateway != NULL)
info->rti_ifa = ifaof_ifpforaddr(gateway, info->rti_ifp);
} else if (dst != NULL && gateway != NULL)
info->rti_ifa = ifa_ifwithroute(flags, dst, gateway,
fibnum);
else if (sa != NULL)
info->rti_ifa = ifa_ifwithroute(flags, sa, sa,
fibnum);
}
if (needref && info->rti_ifa != NULL) {
if (info->rti_ifp == NULL)
info->rti_ifp = info->rti_ifa->ifa_ifp;
ifa_ref(info->rti_ifa);
} else
error = ENETUNREACH;
NET_EPOCH_EXIT(et);
return (error);
}
void
rt_updatemtu(struct ifnet *ifp)
{
struct rib_head *rnh;
int mtu;
int i, j;
/*
* Try to update rt_mtu for all routes using this interface
* Unfortunately the only way to do this is to traverse all
* routing tables in all fibs/domains.
*/
for (i = 1; i <= AF_MAX; i++) {
mtu = if_getmtu_family(ifp, i);
for (j = 0; j < rt_numfibs; j++) {
rnh = rt_tables_get_rnh(j, i);
if (rnh == NULL)
continue;
nhops_update_ifmtu(rnh, ifp, mtu);
}
}
}
#if 0
int p_sockaddr(char *buf, int buflen, struct sockaddr *s);
int rt_print(char *buf, int buflen, struct rtentry *rt);
int
p_sockaddr(char *buf, int buflen, struct sockaddr *s)
{
void *paddr = NULL;
switch (s->sa_family) {
case AF_INET:
paddr = &((struct sockaddr_in *)s)->sin_addr;
break;
case AF_INET6:
paddr = &((struct sockaddr_in6 *)s)->sin6_addr;
break;
}
if (paddr == NULL)
return (0);
if (inet_ntop(s->sa_family, paddr, buf, buflen) == NULL)
return (0);
return (strlen(buf));
}
int
rt_print(char *buf, int buflen, struct rtentry *rt)
{
struct sockaddr *addr, *mask;
int i = 0;
addr = rt_key(rt);
mask = rt_mask(rt);
i = p_sockaddr(buf, buflen, addr);
if (!(rt->rt_flags & RTF_HOST)) {
buf[i++] = '/';
i += p_sockaddr(buf + i, buflen - i, mask);
}
if (rt->rt_flags & RTF_GATEWAY) {
buf[i++] = '>';
i += p_sockaddr(buf + i, buflen - i, &rt->rt_nhop->gw_sa);
}
return (i);
}
#endif
void
rt_maskedcopy(struct sockaddr *src, struct sockaddr *dst, struct sockaddr *netmask)
{
u_char *cp1 = (u_char *)src;
u_char *cp2 = (u_char *)dst;
u_char *cp3 = (u_char *)netmask;
u_char *cplim = cp2 + *cp3;
u_char *cplim2 = cp2 + *cp1;
*cp2++ = *cp1++; *cp2++ = *cp1++; /* copies sa_len & sa_family */
cp3 += 2;
if (cplim > cplim2)
cplim = cplim2;
while (cp2 < cplim)
*cp2++ = *cp1++ & *cp3++;
if (cp2 < cplim2)
bzero((caddr_t)cp2, (unsigned)(cplim2 - cp2));
}
/*
* Announce interface address arrival/withdraw
* Returns 0 on success.
*/
int
rt_addrmsg(int cmd, struct ifaddr *ifa, int fibnum)
{
KASSERT(cmd == RTM_ADD || cmd == RTM_DELETE,
("unexpected cmd %d", cmd));
KASSERT((fibnum >= 0 && fibnum < rt_numfibs),
("%s: fib out of range 0 <=%d<%d", __func__, fibnum, rt_numfibs));
EVENTHANDLER_DIRECT_INVOKE(rt_addrmsg, ifa, cmd);
if (V_rt_add_addr_allfibs)
fibnum = RT_ALL_FIBS;
return (rtsock_addrmsg(cmd, ifa, fibnum));
}
/*
* Announce kernel-originated route addition/removal to rtsock based on @rt data.
* cmd: RTM_ cmd
* @rt: valid rtentry
* @nh: nhop object to announce
* @fibnum: fib id or RT_ALL_FIBS
*
* Returns 0 on success.
*/
int
rt_routemsg(int cmd, struct rtentry *rt, struct nhop_object *nh,
int fibnum)
{
KASSERT(cmd == RTM_ADD || cmd == RTM_DELETE,
("unexpected cmd %d", cmd));
KASSERT(fibnum == RT_ALL_FIBS || (fibnum >= 0 && fibnum < rt_numfibs),
("%s: fib out of range 0 <=%d<%d", __func__, fibnum, rt_numfibs));
KASSERT(rt_key(rt) != NULL, (":%s: rt_key must be supplied", __func__));
return (rtsock_routemsg(cmd, rt, nh, fibnum));
}
/*
* Announce kernel-originated route addition/removal to rtsock based on @rt data.
* cmd: RTM_ cmd
* @info: addrinfo structure with valid data.
* @fibnum: fib id or RT_ALL_FIBS
*
* Returns 0 on success.
*/
int
rt_routemsg_info(int cmd, struct rt_addrinfo *info, int fibnum)
{
KASSERT(cmd == RTM_ADD || cmd == RTM_DELETE || cmd == RTM_CHANGE,
("unexpected cmd %d", cmd));
KASSERT(fibnum == RT_ALL_FIBS || (fibnum >= 0 && fibnum < rt_numfibs),
("%s: fib out of range 0 <=%d<%d", __func__, fibnum, rt_numfibs));
KASSERT(info->rti_info[RTAX_DST] != NULL, (":%s: RTAX_DST must be supplied", __func__));
return (rtsock_routemsg_info(cmd, info, fibnum));
}
-
-/*
- * This is called to generate messages from the routing socket
- * indicating a network interface has had addresses associated with it.
- */
-void
-rt_newaddrmsg_fib(int cmd, struct ifaddr *ifa, struct rtentry *rt, int fibnum)
-{
-
- KASSERT(cmd == RTM_ADD || cmd == RTM_DELETE,
- ("unexpected cmd %u", cmd));
- KASSERT((fibnum >= 0 && fibnum < rt_numfibs),
- ("%s: fib out of range 0 <=%d<%d", __func__, fibnum, rt_numfibs));
-
- if (cmd == RTM_ADD) {
- rt_addrmsg(cmd, ifa, fibnum);
- if (rt != NULL)
- rt_routemsg(cmd, rt, nhop_select(rt->rt_nhop, 0), fibnum);
- } else {
- if (rt != NULL)
- rt_routemsg(cmd, rt, nhop_select(rt->rt_nhop, 0), fibnum);
- rt_addrmsg(cmd, ifa, fibnum);
- }
-}
diff --git a/sys/net/route.h b/sys/net/route.h
index 96a8e78ecb3a..f9928ab6a776 100644
--- a/sys/net/route.h
+++ b/sys/net/route.h
@@ -1,454 +1,449 @@
/*-
* SPDX-License-Identifier: BSD-3-Clause
*
* Copyright (c) 1980, 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.
*
* @(#)route.h 8.4 (Berkeley) 1/9/95
* $FreeBSD$
*/
#ifndef _NET_ROUTE_H_
#define _NET_ROUTE_H_
#include <net/vnet.h>
/*
* Kernel resident routing tables.
*
* The routing tables are initialized when interface addresses
* are set by making entries for all directly connected interfaces.
*/
/*
* Struct route consiste of a destination address,
* a route entry pointer, link-layer prepend data pointer along
* with its length.
*/
struct route {
struct nhop_object *ro_nh;
struct llentry *ro_lle;
/*
* ro_prepend and ro_plen are only used for bpf to pass in a
* preformed header. They are not cacheable.
*/
char *ro_prepend;
uint16_t ro_plen;
uint16_t ro_flags;
uint16_t ro_mtu; /* saved ro_rt mtu */
uint16_t spare;
struct sockaddr ro_dst;
};
#define RT_L2_ME_BIT 2 /* dst L2 addr is our address */
#define RT_MAY_LOOP_BIT 3 /* dst may require loop copy */
#define RT_HAS_HEADER_BIT 4 /* mbuf already have its header prepended */
#define RT_L2_ME (1 << RT_L2_ME_BIT) /* 0x0004 */
#define RT_MAY_LOOP (1 << RT_MAY_LOOP_BIT) /* 0x0008 */
#define RT_HAS_HEADER (1 << RT_HAS_HEADER_BIT) /* 0x0010 */
#define RT_REJECT 0x0020 /* Destination is reject */
#define RT_BLACKHOLE 0x0040 /* Destination is blackhole */
#define RT_HAS_GW 0x0080 /* Destination has GW */
#define RT_LLE_CACHE 0x0100 /* Cache link layer */
struct rt_metrics {
u_long rmx_locks; /* Kernel must leave these values alone */
u_long rmx_mtu; /* MTU for this path */
u_long rmx_hopcount; /* max hops expected */
u_long rmx_expire; /* lifetime for route, e.g. redirect */
u_long rmx_recvpipe; /* inbound delay-bandwidth product */
u_long rmx_sendpipe; /* outbound delay-bandwidth product */
u_long rmx_ssthresh; /* outbound gateway buffer limit */
u_long rmx_rtt; /* estimated round trip time */
u_long rmx_rttvar; /* estimated rtt variance */
u_long rmx_pksent; /* packets sent using this route */
u_long rmx_weight; /* route weight */
u_long rmx_nhidx; /* route nexhop index */
u_long rmx_filler[2]; /* will be used for T/TCP later */
};
/*
* rmx_rtt and rmx_rttvar are stored as microseconds;
* RTTTOPRHZ(rtt) converts to a value suitable for use
* by a protocol slowtimo counter.
*/
#define RTM_RTTUNIT 1000000 /* units for rtt, rttvar, as units per sec */
#define RTTTOPRHZ(r) ((r) / (RTM_RTTUNIT / PR_SLOWHZ))
/* lle state is exported in rmx_state rt_metrics field */
#define rmx_state rmx_weight
/* default route weight */
#define RT_DEFAULT_WEIGHT 1
#define RT_MAX_WEIGHT 16777215 /* 3 bytes */
/*
* Keep a generation count of routing table, incremented on route addition,
* so we can invalidate caches. This is accessed without a lock, as precision
* is not required.
*/
typedef volatile u_int rt_gen_t; /* tree generation (for adds) */
#define RT_GEN(fibnum, af) rt_tables_get_gen(fibnum, af)
#define RT_DEFAULT_FIB 0 /* Explicitly mark fib=0 restricted cases */
#define RT_ALL_FIBS -1 /* Announce event for every fib */
#ifdef _KERNEL
VNET_DECLARE(uint32_t, _rt_numfibs); /* number of existing route tables */
#define V_rt_numfibs VNET(_rt_numfibs)
/* temporary compat arg */
#define rt_numfibs V_rt_numfibs
VNET_DECLARE(u_int, rt_add_addr_allfibs); /* Announce interfaces to all fibs */
#define V_rt_add_addr_allfibs VNET(rt_add_addr_allfibs)
/* Calculate flowid for locally-originated packets */
#define V_fib_hash_outbound VNET(fib_hash_outbound)
VNET_DECLARE(u_int, fib_hash_outbound);
/* Outbound flowid generation rules */
#ifdef RSS
#define fib4_calc_packet_hash xps_proto_software_hash_v4
#define fib6_calc_packet_hash xps_proto_software_hash_v6
#define CALC_FLOWID_OUTBOUND_SENDTO true
#ifdef ROUTE_MPATH
#define CALC_FLOWID_OUTBOUND V_fib_hash_outbound
#else
#define CALC_FLOWID_OUTBOUND false
#endif
#else /* !RSS */
#define fib4_calc_packet_hash fib4_calc_software_hash
#define fib6_calc_packet_hash fib6_calc_software_hash
#ifdef ROUTE_MPATH
#define CALC_FLOWID_OUTBOUND_SENDTO V_fib_hash_outbound
#define CALC_FLOWID_OUTBOUND V_fib_hash_outbound
#else
#define CALC_FLOWID_OUTBOUND_SENDTO false
#define CALC_FLOWID_OUTBOUND false
#endif
#endif /* RSS */
#endif /* _KERNEL */
/*
* We distinguish between routes to hosts and routes to networks,
* preferring the former if available. For each route we infer
* the interface to use from the gateway address supplied when
* the route was entered. Routes that forward packets through
* gateways are marked so that the output routines know to address the
* gateway rather than the ultimate destination.
*/
#define RTF_UP 0x1 /* route usable */
#define RTF_GATEWAY 0x2 /* destination is a gateway */
#define RTF_HOST 0x4 /* host entry (net otherwise) */
#define RTF_REJECT 0x8 /* host or net unreachable */
#define RTF_DYNAMIC 0x10 /* created dynamically (by redirect) */
#define RTF_MODIFIED 0x20 /* modified dynamically (by redirect) */
#define RTF_DONE 0x40 /* message confirmed */
/* 0x80 unused, was RTF_DELCLONE */
/* 0x100 unused, was RTF_CLONING */
#define RTF_XRESOLVE 0x200 /* external daemon resolves name */
#define RTF_LLINFO 0x400 /* DEPRECATED - exists ONLY for backward
compatibility */
#define RTF_LLDATA 0x400 /* used by apps to add/del L2 entries */
#define RTF_STATIC 0x800 /* manually added */
#define RTF_BLACKHOLE 0x1000 /* just discard pkts (during updates) */
#define RTF_PROTO2 0x4000 /* protocol specific routing flag */
#define RTF_PROTO1 0x8000 /* protocol specific routing flag */
/* 0x10000 unused, was RTF_PRCLONING */
/* 0x20000 unused, was RTF_WASCLONED */
#define RTF_PROTO3 0x40000 /* protocol specific routing flag */
#define RTF_FIXEDMTU 0x80000 /* MTU was explicitly specified */
#define RTF_PINNED 0x100000 /* route is immutable */
#define RTF_LOCAL 0x200000 /* route represents a local address */
#define RTF_BROADCAST 0x400000 /* route represents a bcast address */
#define RTF_MULTICAST 0x800000 /* route represents a mcast address */
/* 0x8000000 and up unassigned */
#define RTF_STICKY 0x10000000 /* always route dst->src */
#define RTF_RNH_LOCKED 0x40000000 /* radix node head is locked */
#define RTF_GWFLAG_COMPAT 0x80000000 /* a compatibility bit for interacting
with existing routing apps */
/* Mask of RTF flags that are allowed to be modified by RTM_CHANGE. */
#define RTF_FMASK \
(RTF_PROTO1 | RTF_PROTO2 | RTF_PROTO3 | RTF_BLACKHOLE | \
RTF_REJECT | RTF_STATIC | RTF_STICKY)
/*
* fib_ nexthop API flags.
*/
/* Consumer-visible nexthop info flags */
#define NHF_MULTIPATH 0x0008 /* Nexhop is a nexthop group */
#define NHF_REJECT 0x0010 /* RTF_REJECT */
#define NHF_BLACKHOLE 0x0020 /* RTF_BLACKHOLE */
#define NHF_REDIRECT 0x0040 /* RTF_DYNAMIC|RTF_MODIFIED */
#define NHF_DEFAULT 0x0080 /* Default route */
#define NHF_BROADCAST 0x0100 /* RTF_BROADCAST */
#define NHF_GATEWAY 0x0200 /* RTF_GATEWAY */
#define NHF_HOST 0x0400 /* RTF_HOST */
/* Nexthop request flags */
#define NHR_NONE 0x00 /* empty flags field */
#define NHR_REF 0x01 /* reference nexhop */
#define NHR_NODEFAULT 0x02 /* uRPF: do not consider default route */
/* Control plane route request flags */
#define NHR_COPY 0x100 /* Copy rte data */
#define NHR_UNLOCKED 0x200 /* Do not lock table */
/*
* Routing statistics.
*/
struct rtstat {
uint64_t rts_badredirect; /* bogus redirect calls */
uint64_t rts_dynamic; /* routes created by redirects */
uint64_t rts_newgateway; /* routes modified by redirects */
uint64_t rts_unreach; /* lookups which failed */
uint64_t rts_wildcard; /* lookups satisfied by a wildcard */
uint64_t rts_nh_idx_alloc_failure; /* nexthop index alloc failure*/
uint64_t rts_nh_alloc_failure; /* nexthop allocation failure*/
uint64_t rts_add_failure; /* # of route addition failures */
uint64_t rts_add_retry; /* # of route addition retries */
uint64_t rts_del_failure; /* # of route deletion failure */
uint64_t rts_del_retry; /* # of route deletion retries */
};
/*
* Structures for routing messages.
*/
struct rt_msghdr {
u_short rtm_msglen; /* to skip over non-understood messages */
u_char rtm_version; /* future binary compatibility */
u_char rtm_type; /* message type */
u_short rtm_index; /* index for associated ifp */
u_short _rtm_spare1;
int rtm_flags; /* flags, incl. kern & message, e.g. DONE */
int rtm_addrs; /* bitmask identifying sockaddrs in msg */
pid_t rtm_pid; /* identify sender */
int rtm_seq; /* for sender to identify action */
int rtm_errno; /* why failed */
int rtm_fmask; /* bitmask used in RTM_CHANGE message */
u_long rtm_inits; /* which metrics we are initializing */
struct rt_metrics rtm_rmx; /* metrics themselves */
};
#define RTM_VERSION 5 /* Up the ante and ignore older versions */
/*
* Message types.
*
* The format for each message is annotated below using the following
* identifiers:
*
* (1) struct rt_msghdr
* (2) struct ifa_msghdr
* (3) struct if_msghdr
* (4) struct ifma_msghdr
* (5) struct if_announcemsghdr
*
*/
#define RTM_ADD 0x1 /* (1) Add Route */
#define RTM_DELETE 0x2 /* (1) Delete Route */
#define RTM_CHANGE 0x3 /* (1) Change Metrics or flags */
#define RTM_GET 0x4 /* (1) Report Metrics */
#define RTM_LOSING 0x5 /* (1) Kernel Suspects Partitioning */
#define RTM_REDIRECT 0x6 /* (1) Told to use different route */
#define RTM_MISS 0x7 /* (1) Lookup failed on this address */
#define RTM_LOCK 0x8 /* (1) fix specified metrics */
/* 0x9 */
/* 0xa */
#define RTM_RESOLVE 0xb /* (1) req to resolve dst to LL addr */
#define RTM_NEWADDR 0xc /* (2) address being added to iface */
#define RTM_DELADDR 0xd /* (2) address being removed from iface */
#define RTM_IFINFO 0xe /* (3) iface going up/down etc. */
#define RTM_NEWMADDR 0xf /* (4) mcast group membership being added to if */
#define RTM_DELMADDR 0x10 /* (4) mcast group membership being deleted */
#define RTM_IFANNOUNCE 0x11 /* (5) iface arrival/departure */
#define RTM_IEEE80211 0x12 /* (5) IEEE80211 wireless event */
/*
* Bitmask values for rtm_inits and rmx_locks.
*/
#define RTV_MTU 0x1 /* init or lock _mtu */
#define RTV_HOPCOUNT 0x2 /* init or lock _hopcount */
#define RTV_EXPIRE 0x4 /* init or lock _expire */
#define RTV_RPIPE 0x8 /* init or lock _recvpipe */
#define RTV_SPIPE 0x10 /* init or lock _sendpipe */
#define RTV_SSTHRESH 0x20 /* init or lock _ssthresh */
#define RTV_RTT 0x40 /* init or lock _rtt */
#define RTV_RTTVAR 0x80 /* init or lock _rttvar */
#define RTV_WEIGHT 0x100 /* init or lock _weight */
/*
* Bitmask values for rtm_addrs.
*/
#define RTA_DST 0x1 /* destination sockaddr present */
#define RTA_GATEWAY 0x2 /* gateway sockaddr present */
#define RTA_NETMASK 0x4 /* netmask sockaddr present */
#define RTA_GENMASK 0x8 /* cloning mask sockaddr present */
#define RTA_IFP 0x10 /* interface name sockaddr present */
#define RTA_IFA 0x20 /* interface addr sockaddr present */
#define RTA_AUTHOR 0x40 /* sockaddr for author of redirect */
#define RTA_BRD 0x80 /* for NEWADDR, broadcast or p-p dest addr */
/*
* Index offsets for sockaddr array for alternate internal encoding.
*/
#define RTAX_DST 0 /* destination sockaddr present */
#define RTAX_GATEWAY 1 /* gateway sockaddr present */
#define RTAX_NETMASK 2 /* netmask sockaddr present */
#define RTAX_GENMASK 3 /* cloning mask sockaddr present */
#define RTAX_IFP 4 /* interface name sockaddr present */
#define RTAX_IFA 5 /* interface addr sockaddr present */
#define RTAX_AUTHOR 6 /* sockaddr for author of redirect */
#define RTAX_BRD 7 /* for NEWADDR, broadcast or p-p dest addr */
#define RTAX_MAX 8 /* size of array to allocate */
struct rtentry;
struct nhop_object;
typedef int rib_filter_f_t(const struct rtentry *, const struct nhop_object *,
void *);
struct rt_addrinfo {
int rti_addrs; /* Route RTF_ flags */
int rti_flags; /* Route RTF_ flags */
struct sockaddr *rti_info[RTAX_MAX]; /* Sockaddr data */
struct ifaddr *rti_ifa; /* value of rt_ifa addr */
struct ifnet *rti_ifp; /* route interface */
rib_filter_f_t *rti_filter; /* filter function */
void *rti_filterdata; /* filter paramenters */
u_long rti_mflags; /* metrics RTV_ flags */
u_long rti_spare; /* Will be used for fib */
struct rt_metrics *rti_rmx; /* Pointer to route metrics */
};
/*
* This macro returns the size of a struct sockaddr when passed
* through a routing socket. Basically we round up sa_len to
* a multiple of sizeof(long), with a minimum of sizeof(long).
* The case sa_len == 0 should only apply to empty structures.
*/
#define SA_SIZE(sa) \
( (((struct sockaddr *)(sa))->sa_len == 0) ? \
sizeof(long) : \
1 + ( (((struct sockaddr *)(sa))->sa_len - 1) | (sizeof(long) - 1) ) )
#define sa_equal(a, b) ( \
(((const struct sockaddr *)(a))->sa_len == ((const struct sockaddr *)(b))->sa_len) && \
(bcmp((a), (b), ((const struct sockaddr *)(b))->sa_len) == 0))
#ifdef _KERNEL
#define RT_LINK_IS_UP(ifp) (!((ifp)->if_capabilities & IFCAP_LINKSTATE) \
|| (ifp)->if_link_state == LINK_STATE_UP)
#define RO_NHFREE(_ro) do { \
if ((_ro)->ro_nh) { \
NH_FREE((_ro)->ro_nh); \
(_ro)->ro_nh = NULL; \
} \
} while (0)
#define RO_INVALIDATE_CACHE(ro) do { \
if ((ro)->ro_lle != NULL) { \
LLE_FREE((ro)->ro_lle); \
(ro)->ro_lle = NULL; \
} \
if ((ro)->ro_nh != NULL) { \
NH_FREE((ro)->ro_nh); \
(ro)->ro_nh = NULL; \
} \
} while (0)
/*
* Validate a cached route based on a supplied cookie. If there is an
* out-of-date cache, simply free it. Update the generation number
* for the new allocation
*/
#define NH_VALIDATE(ro, cookiep, fibnum) do { \
rt_gen_t cookie = RT_GEN(fibnum, (ro)->ro_dst.sa_family); \
if (*(cookiep) != cookie) { \
RO_INVALIDATE_CACHE(ro); \
*(cookiep) = cookie; \
} \
} while (0)
struct ifmultiaddr;
struct rib_head;
void rt_ieee80211msg(struct ifnet *, int, void *, size_t);
void rt_ifannouncemsg(struct ifnet *, int);
void rt_ifmsg(struct ifnet *);
void rt_missmsg(int, struct rt_addrinfo *, int, int);
void rt_missmsg_fib(int, struct rt_addrinfo *, int, int, int);
-void rt_newaddrmsg_fib(int, struct ifaddr *, struct rtentry *, int);
int rt_addrmsg(int, struct ifaddr *, int);
int rt_routemsg(int, struct rtentry *, struct nhop_object *, int);
int rt_routemsg_info(int, struct rt_addrinfo *, int);
void rt_newmaddrmsg(int, struct ifmultiaddr *);
void rt_maskedcopy(struct sockaddr *, struct sockaddr *, struct sockaddr *);
struct rib_head *rt_table_init(int, int, u_int);
void rt_table_destroy(struct rib_head *);
u_int rt_tables_get_gen(uint32_t table, sa_family_t family);
struct sockaddr *rtsock_fix_netmask(const struct sockaddr *dst,
const struct sockaddr *smask, struct sockaddr_storage *dmask);
void rt_updatemtu(struct ifnet *);
void rt_flushifroutes_af(struct ifnet *, int);
void rt_flushifroutes(struct ifnet *ifp);
-/* XXX MRT COMPAT VERSIONS THAT SET UNIVERSE to 0 */
-/* Thes are used by old code not yet converted to use multiple FIBS */
-int rtinit(struct ifaddr *, int, int);
-
/* XXX MRT NEW VERSIONS THAT USE FIBs
* For now the protocol indepedent versions are the same as the AF_INET ones
* but this will change..
*/
int rtioctl_fib(u_long, caddr_t, u_int);
int rib_lookup_info(uint32_t, const struct sockaddr *, uint32_t, uint32_t,
struct rt_addrinfo *);
void rib_free_info(struct rt_addrinfo *info);
/* New API */
struct nhop_object *rib_lookup(uint32_t fibnum, const struct sockaddr *dst,
uint32_t flags, uint32_t flowid);
#endif
#endif
diff --git a/sys/net/route/route_ctl.h b/sys/net/route/route_ctl.h
index c52c6b96e126..ecbc9ee91dc0 100644
--- a/sys/net/route/route_ctl.h
+++ b/sys/net/route/route_ctl.h
@@ -1,148 +1,149 @@
/*-
* SPDX-License-Identifier: BSD-2-Clause-FreeBSD
*
* Copyright (c) 2020 Alexander V. Chernikov
*
* 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 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 AUTHOR 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.
*
* $FreeBSD$
*/
/*
* This header file contains public functions and structures used for
* routing table manipulations.
*/
#ifndef _NET_ROUTE_ROUTE_CTL_H_
#define _NET_ROUTE_ROUTE_CTL_H_
struct rib_cmd_info {
uint8_t rc_cmd; /* RTM_ADD|RTM_DEL|RTM_CHANGE */
uint8_t spare[3];
uint32_t rc_nh_weight; /* new nhop weight */
struct rtentry *rc_rt; /* Target entry */
struct nhop_object *rc_nh_old; /* Target nhop OR mpath */
struct nhop_object *rc_nh_new; /* Target nhop OR mpath */
};
int rib_add_route(uint32_t fibnum, struct rt_addrinfo *info,
struct rib_cmd_info *rc);
int rib_del_route(uint32_t fibnum, struct rt_addrinfo *info,
struct rib_cmd_info *rc);
int rib_change_route(uint32_t fibnum, struct rt_addrinfo *info,
struct rib_cmd_info *rc);
int rib_action(uint32_t fibnum, int action, struct rt_addrinfo *info,
struct rib_cmd_info *rc);
+int rib_handle_ifaddr_info(uint32_t fibnum, int cmd, struct rt_addrinfo *info);
typedef void route_notification_t(struct rib_cmd_info *rc, void *);
void rib_decompose_notification(struct rib_cmd_info *rc,
route_notification_t *cb, void *cbdata);
int rib_add_redirect(u_int fibnum, struct sockaddr *dst,
struct sockaddr *gateway, struct sockaddr *author, struct ifnet *ifp,
int flags, int expire_sec);
enum rib_walk_hook {
RIB_WALK_HOOK_PRE, /* Hook is called before iteration */
RIB_WALK_HOOK_POST, /* Hook is called after iteration */
};
typedef int rib_walktree_f_t(struct rtentry *, void *);
typedef void rib_walk_hook_f_t(struct rib_head *rnh, enum rib_walk_hook stage,
void *arg);
void rib_walk(uint32_t fibnum, int af, bool wlock, rib_walktree_f_t *wa_f,
void *arg);
void rib_walk_ext(uint32_t fibnum, int af, bool wlock, rib_walktree_f_t *wa_f,
rib_walk_hook_f_t *hook_f, void *arg);
void rib_walk_ext_internal(struct rib_head *rnh, bool wlock,
rib_walktree_f_t *wa_f, rib_walk_hook_f_t *hook_f, void *arg);
void rib_walk_del(u_int fibnum, int family, rib_filter_f_t *filter_f,
void *arg, bool report);
void rib_foreach_table_walk(int family, bool wlock, rib_walktree_f_t *wa_f,
rib_walk_hook_f_t *hook_f, void *arg);
void rib_foreach_table_walk_del(int family, rib_filter_f_t *filter_f, void *arg);
struct nhop_object;
struct nhgrp_object;
struct route_nhop_data {
union {
struct nhop_object *rnd_nhop;
struct nhgrp_object *rnd_nhgrp;
};
uint32_t rnd_weight;
};
const struct rtentry *rib_lookup_prefix(uint32_t fibnum, int family,
const struct sockaddr *dst, const struct sockaddr *netmask,
struct route_nhop_data *rnd);
const struct rtentry *rib_lookup_lpm(uint32_t fibnum, int family,
const struct sockaddr *dst, struct route_nhop_data *rnd);
/* rtentry accessors */
bool rt_is_host(const struct rtentry *rt);
sa_family_t rt_get_family(const struct rtentry *);
struct nhop_object *rt_get_raw_nhop(const struct rtentry *rt);
#ifdef INET
struct in_addr;
void rt_get_inet_prefix_plen(const struct rtentry *rt, struct in_addr *paddr,
int *plen, uint32_t *pscopeid);
void rt_get_inet_prefix_pmask(const struct rtentry *rt, struct in_addr *paddr,
struct in_addr *pmask, uint32_t *pscopeid);
#endif
#ifdef INET6
struct in6_addr;
void rt_get_inet6_prefix_plen(const struct rtentry *rt, struct in6_addr *paddr,
int *plen, uint32_t *pscopeid);
void rt_get_inet6_prefix_pmask(const struct rtentry *rt, struct in6_addr *paddr,
struct in6_addr *pmask, uint32_t *pscopeid);
#endif
/* Nexthops */
uint32_t nhops_get_count(struct rib_head *rh);
/* Multipath */
struct weightened_nhop;
struct weightened_nhop *nhgrp_get_nhops(struct nhgrp_object *nhg,
uint32_t *pnum_nhops);
uint32_t nhgrp_get_count(struct rib_head *rh);
/* Route subscriptions */
enum rib_subscription_type {
RIB_NOTIFY_IMMEDIATE,
RIB_NOTIFY_DELAYED
};
struct rib_subscription;
typedef void rib_subscription_cb_t(struct rib_head *rnh, struct rib_cmd_info *rc,
void *arg);
struct rib_subscription *rib_subscribe(uint32_t fibnum, int family,
rib_subscription_cb_t *f, void *arg, enum rib_subscription_type type,
bool waitok);
struct rib_subscription *rib_subscribe_internal(struct rib_head *rnh,
rib_subscription_cb_t *f, void *arg, enum rib_subscription_type type,
bool waitok);
void rib_unsibscribe(struct rib_subscription *rs);
#endif
diff --git a/sys/net/route/route_ifaddrs.c b/sys/net/route/route_ifaddrs.c
index 967aa5d75e68..6e264327d66d 100644
--- a/sys/net/route/route_ifaddrs.c
+++ b/sys/net/route/route_ifaddrs.c
@@ -1,308 +1,206 @@
/*-
* SPDX-License-Identifier: BSD-3-Clause
*
* Copyright (c) 1980, 1986, 1991, 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.
*
* @(#)route.c 8.3.1.1 (Berkeley) 2/23/95
* $FreeBSD$
*/
#include "opt_route.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/malloc.h>
#include <sys/socket.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/rmlock.h>
#include <net/if.h>
#include <net/if_var.h>
#include <net/if_dl.h>
#include <net/route.h>
#include <net/route/route_ctl.h>
#include <net/route/route_var.h>
#include <net/route/nhop.h>
#include <net/vnet.h>
#include <netinet/in.h>
/*
* Control interface address fib propagation.
* By default, interface address routes are added to the fib of the interface.
* Once set to non-zero, adds interface address route to all fibs.
*/
VNET_DEFINE(u_int, rt_add_addr_allfibs) = 0;
SYSCTL_UINT(_net, OID_AUTO, add_addr_allfibs, CTLFLAG_RWTUN | CTLFLAG_VNET,
&VNET_NAME(rt_add_addr_allfibs), 0, "");
/*
- * Set up a routing table entry, normally
- * for an interface.
+ * Executes routing tables change specified by @cmd and @info for the fib
+ * @fibnum. Generates routing message on success.
+ * Note: it assumes there is only single route (interface route) for the
+ * provided prefix.
+ * Returns 0 on success or errno.
*/
-static inline int
-rtinit1(struct ifaddr *ifa, int cmd, int flags, int fibnum)
+static int
+rib_handle_ifaddr_one(uint32_t fibnum, int cmd, struct rt_addrinfo *info)
{
- RIB_RLOCK_TRACKER;
- struct epoch_tracker et;
- struct sockaddr *dst;
- struct sockaddr *netmask;
struct rib_cmd_info rc;
- struct rt_addrinfo info;
- int error = 0;
- int startfib, endfib;
- struct sockaddr_storage ss;
- int didwork = 0;
- int a_failure = 0;
- struct sockaddr_dl_short sdl;
- struct rib_head *rnh;
+ struct nhop_object *nh;
+ int error;
- if (flags & RTF_HOST) {
- dst = ifa->ifa_dstaddr;
- netmask = NULL;
- } else {
- dst = ifa->ifa_addr;
- netmask = ifa->ifa_netmask;
- }
- if (dst->sa_len == 0)
- return(EINVAL);
- switch (dst->sa_family) {
- case AF_INET6:
- case AF_INET:
- /* We support multiple FIBs. */
- break;
- default:
- fibnum = RT_DEFAULT_FIB;
- break;
- }
- if (fibnum == RT_ALL_FIBS) {
- if (V_rt_add_addr_allfibs == 0 && cmd == (int)RTM_ADD)
- startfib = endfib = ifa->ifa_ifp->if_fib;
- else {
- startfib = 0;
- endfib = rt_numfibs - 1;
- }
- } else {
- KASSERT((fibnum < rt_numfibs), ("rtinit1: bad fibnum"));
- startfib = fibnum;
- endfib = fibnum;
+ error = rib_action(fibnum, cmd, info, &rc);
+ if (error == 0) {
+ if (cmd == RTM_ADD)
+ nh = nhop_select(rc.rc_nh_new, 0);
+ else
+ nh = nhop_select(rc.rc_nh_old, 0);
+ rt_routemsg(cmd, rc.rc_rt, nh, fibnum);
}
- /*
- * If it's a delete, check that if it exists,
- * it's on the correct interface or we might scrub
- * a route to another ifa which would
- * be confusing at best and possibly worse.
- */
- if (cmd == RTM_DELETE) {
- /*
- * It's a delete, so it should already exist..
- * If it's a net, mask off the host bits
- * (Assuming we have a mask)
- * XXX this is kinda inet specific..
- */
- if (netmask != NULL) {
- rt_maskedcopy(dst, (struct sockaddr *)&ss, netmask);
- dst = (struct sockaddr *)&ss;
- }
- }
- bzero(&sdl, sizeof(struct sockaddr_dl_short));
- sdl.sdl_family = AF_LINK;
- sdl.sdl_len = sizeof(struct sockaddr_dl_short);
- sdl.sdl_type = ifa->ifa_ifp->if_type;
- sdl.sdl_index = ifa->ifa_ifp->if_index;
- /*
- * Now go through all the requested tables (fibs) and do the
- * requested action. Realistically, this will either be fib 0
- * for protocols that don't do multiple tables or all the
- * tables for those that do.
- */
- for ( fibnum = startfib; fibnum <= endfib; fibnum++) {
- if (cmd == RTM_DELETE) {
- struct radix_node *rn;
- /*
- * Look up an rtentry that is in the routing tree and
- * contains the correct info.
- */
- rnh = rt_tables_get_rnh(fibnum, dst->sa_family);
- if (rnh == NULL)
- /* this table doesn't exist but others might */
- continue;
- RIB_RLOCK(rnh);
- rn = rnh->rnh_lookup(dst, netmask, &rnh->head);
- error = (rn == NULL ||
- (rn->rn_flags & RNF_ROOT) ||
- RNTORT(rn)->rt_nhop->nh_ifa != ifa);
- RIB_RUNLOCK(rnh);
- if (error) {
- /* this is only an error if bad on ALL tables */
- continue;
- }
- }
- /*
- * Do the actual request
- */
- bzero((caddr_t)&info, sizeof(info));
- info.rti_ifa = ifa;
- info.rti_flags = flags |
- (ifa->ifa_flags & ~IFA_RTSELF) | RTF_PINNED;
- info.rti_info[RTAX_DST] = dst;
- info.rti_info[RTAX_GATEWAY] = (struct sockaddr *)&sdl;
- info.rti_info[RTAX_NETMASK] = netmask;
- NET_EPOCH_ENTER(et);
- error = rib_action(fibnum, cmd, &info, &rc);
- if (error == 0 && rc.rc_rt != NULL) {
- /*
- * notify any listening routing agents of the change
- */
+ return (error);
+}
- /* TODO: interface routes/aliases */
- rt_newaddrmsg_fib(cmd, ifa, rc.rc_rt, fibnum);
- didwork = 1;
+/*
+ * Adds/deletes interface prefix specified by @info to the routing table.
+ * If V_rt_add_addr_allfibs is set, iterates over all existing routing
+ * tables, otherwise uses fib in @fibnum. Generates routing message for
+ * each table.
+ * Returns 0 on success or errno.
+ */
+int
+rib_handle_ifaddr_info(uint32_t fibnum, int cmd, struct rt_addrinfo *info)
+{
+ int error, last_error = 0;
+ bool didwork = false;
+
+ if (V_rt_add_addr_allfibs == 0) {
+ error = rib_handle_ifaddr_one(fibnum, cmd, info);
+ didwork = (error == 0);
+ } else {
+ for (fibnum = 0; fibnum < V_rt_numfibs; fibnum++) {
+ error = rib_handle_ifaddr_one(fibnum, cmd, info);
+ if (error == 0)
+ didwork = true;
+ else
+ last_error = error;
}
- NET_EPOCH_EXIT(et);
- if (error)
- a_failure = error;
}
+
if (cmd == RTM_DELETE) {
if (didwork) {
error = 0;
} else {
/* we only give an error if it wasn't in any table */
- error = ((flags & RTF_HOST) ?
+ error = ((info->rti_flags & RTF_HOST) ?
EHOSTUNREACH : ENETUNREACH);
}
} else {
- if (a_failure) {
+ if (last_error != 0) {
/* return an error if any of them failed */
- error = a_failure;
+ error = last_error;
}
}
return (error);
}
-/*
- * Set up a routing table entry, normally
- * for an interface.
- */
-int
-rtinit(struct ifaddr *ifa, int cmd, int flags)
-{
- struct sockaddr *dst;
- int fib = RT_DEFAULT_FIB;
-
- if (flags & RTF_HOST) {
- dst = ifa->ifa_dstaddr;
- } else {
- dst = ifa->ifa_addr;
- }
-
- switch (dst->sa_family) {
- case AF_INET6:
- case AF_INET:
- /* We do support multiple FIBs. */
- fib = RT_ALL_FIBS;
- break;
- }
- return (rtinit1(ifa, cmd, flags, fib));
-}
-
static int
ifa_maintain_loopback_route(int cmd, const char *otype, struct ifaddr *ifa,
struct sockaddr *ia)
{
struct rib_cmd_info rc;
struct epoch_tracker et;
int error;
struct rt_addrinfo info;
struct sockaddr_dl null_sdl;
struct ifnet *ifp;
struct ifaddr *rti_ifa = NULL;
ifp = ifa->ifa_ifp;
NET_EPOCH_ENTER(et);
bzero(&info, sizeof(info));
if (cmd != RTM_DELETE)
info.rti_ifp = V_loif;
if (cmd == RTM_ADD) {
/* explicitly specify (loopback) ifa */
if (info.rti_ifp != NULL) {
rti_ifa = ifaof_ifpforaddr(ifa->ifa_addr, info.rti_ifp);
if (rti_ifa != NULL)
ifa_ref(rti_ifa);
info.rti_ifa = rti_ifa;
}
}
info.rti_flags = ifa->ifa_flags | RTF_HOST | RTF_STATIC | RTF_PINNED;
info.rti_info[RTAX_DST] = ia;
info.rti_info[RTAX_GATEWAY] = (struct sockaddr *)&null_sdl;
link_init_sdl(ifp, (struct sockaddr *)&null_sdl, ifp->if_type);
error = rib_action(ifp->if_fib, cmd, &info, &rc);
NET_EPOCH_EXIT(et);
if (rti_ifa != NULL)
ifa_free(rti_ifa);
if (error == 0 ||
(cmd == RTM_ADD && error == EEXIST) ||
(cmd == RTM_DELETE && (error == ENOENT || error == ESRCH)))
return (error);
log(LOG_DEBUG, "%s: %s failed for interface %s: %u\n",
__func__, otype, if_name(ifp), error);
return (error);
}
int
ifa_add_loopback_route(struct ifaddr *ifa, struct sockaddr *ia)
{
return (ifa_maintain_loopback_route(RTM_ADD, "insertion", ifa, ia));
}
int
ifa_del_loopback_route(struct ifaddr *ifa, struct sockaddr *ia)
{
return (ifa_maintain_loopback_route(RTM_DELETE, "deletion", ifa, ia));
}
int
ifa_switch_loopback_route(struct ifaddr *ifa, struct sockaddr *ia)
{
return (ifa_maintain_loopback_route(RTM_CHANGE, "switch", ifa, ia));
}
diff --git a/sys/netinet/in.c b/sys/netinet/in.c
index cf6541dca879..d6c0c350dec5 100644
--- a/sys/netinet/in.c
+++ b/sys/netinet/in.c
@@ -1,1573 +1,1694 @@
/*-
* SPDX-License-Identifier: BSD-3-Clause
*
* Copyright (c) 1982, 1986, 1991, 1993
* The Regents of the University of California. All rights reserved.
* Copyright (C) 2001 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 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.
*
* @(#)in.c 8.4 (Berkeley) 1/9/95
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <sys/param.h>
#include <sys/eventhandler.h>
#include <sys/systm.h>
#include <sys/sockio.h>
#include <sys/malloc.h>
#include <sys/priv.h>
#include <sys/socket.h>
#include <sys/jail.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/proc.h>
#include <sys/rmlock.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>
#include <sys/sx.h>
#include <net/if.h>
#include <net/if_var.h>
#include <net/if_arp.h>
#include <net/if_dl.h>
#include <net/if_llatbl.h>
#include <net/if_types.h>
#include <net/route.h>
+#include <net/route/nhop.h>
+#include <net/route/route_ctl.h>
#include <net/vnet.h>
#include <netinet/if_ether.h>
#include <netinet/in.h>
#include <netinet/in_var.h>
#include <netinet/in_pcb.h>
#include <netinet/ip_var.h>
#include <netinet/ip_carp.h>
#include <netinet/igmp_var.h>
#include <netinet/udp.h>
#include <netinet/udp_var.h>
static int in_aifaddr_ioctl(u_long, caddr_t, struct ifnet *, struct thread *);
static int in_difaddr_ioctl(u_long, caddr_t, struct ifnet *, struct thread *);
static int in_gifaddr_ioctl(u_long, caddr_t, struct ifnet *, struct thread *);
static void in_socktrim(struct sockaddr_in *);
static void in_purgemaddrs(struct ifnet *);
VNET_DEFINE_STATIC(int, nosameprefix);
#define V_nosameprefix VNET(nosameprefix)
SYSCTL_INT(_net_inet_ip, OID_AUTO, no_same_prefix, CTLFLAG_VNET | CTLFLAG_RW,
&VNET_NAME(nosameprefix), 0,
"Refuse to create same prefixes on different interfaces");
VNET_DECLARE(struct inpcbinfo, ripcbinfo);
#define V_ripcbinfo VNET(ripcbinfo)
static struct sx in_control_sx;
SX_SYSINIT(in_control_sx, &in_control_sx, "in_control");
/*
* Return 1 if an internet address is for a ``local'' host
* (one to which we have a connection).
*/
int
in_localaddr(struct in_addr in)
{
struct rm_priotracker in_ifa_tracker;
u_long i = ntohl(in.s_addr);
struct in_ifaddr *ia;
IN_IFADDR_RLOCK(&in_ifa_tracker);
CK_STAILQ_FOREACH(ia, &V_in_ifaddrhead, ia_link) {
if ((i & ia->ia_subnetmask) == ia->ia_subnet) {
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
return (1);
}
}
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
return (0);
}
/*
* Return 1 if an internet address is for the local host and configured
* on one of its interfaces.
*/
int
in_localip(struct in_addr in)
{
struct rm_priotracker in_ifa_tracker;
struct in_ifaddr *ia;
IN_IFADDR_RLOCK(&in_ifa_tracker);
LIST_FOREACH(ia, INADDR_HASH(in.s_addr), ia_hash) {
if (IA_SIN(ia)->sin_addr.s_addr == in.s_addr) {
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
return (1);
}
}
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
return (0);
}
/*
* Return 1 if an internet address is configured on an interface.
*/
int
in_ifhasaddr(struct ifnet *ifp, struct in_addr in)
{
struct ifaddr *ifa;
struct in_ifaddr *ia;
NET_EPOCH_ASSERT();
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family != AF_INET)
continue;
ia = (struct in_ifaddr *)ifa;
if (ia->ia_addr.sin_addr.s_addr == in.s_addr)
return (1);
}
return (0);
}
/*
* Return a reference to the interface address which is different to
* the supplied one but with same IP address value.
*/
static struct in_ifaddr *
in_localip_more(struct in_ifaddr *ia)
{
struct rm_priotracker in_ifa_tracker;
in_addr_t in = IA_SIN(ia)->sin_addr.s_addr;
struct in_ifaddr *it;
IN_IFADDR_RLOCK(&in_ifa_tracker);
LIST_FOREACH(it, INADDR_HASH(in), ia_hash) {
if (it != ia && IA_SIN(it)->sin_addr.s_addr == in) {
ifa_ref(&it->ia_ifa);
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
return (it);
}
}
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
return (NULL);
}
/*
* Determine whether an IP address is in a reserved set of addresses
* that may not be forwarded, or whether datagrams to that destination
* may be forwarded.
*/
int
in_canforward(struct in_addr in)
{
u_long i = ntohl(in.s_addr);
if (IN_EXPERIMENTAL(i) || IN_MULTICAST(i) || IN_LINKLOCAL(i) ||
IN_ZERONET(i) || IN_LOOPBACK(i))
return (0);
return (1);
}
/*
* Trim a mask in a sockaddr
*/
static void
in_socktrim(struct sockaddr_in *ap)
{
char *cplim = (char *) &ap->sin_addr;
char *cp = (char *) (&ap->sin_addr + 1);
ap->sin_len = 0;
while (--cp >= cplim)
if (*cp) {
(ap)->sin_len = cp - (char *) (ap) + 1;
break;
}
}
/*
* Generic internet control operations (ioctl's).
*/
int
in_control(struct socket *so, u_long cmd, caddr_t data, struct ifnet *ifp,
struct thread *td)
{
struct ifreq *ifr = (struct ifreq *)data;
struct sockaddr_in *addr = (struct sockaddr_in *)&ifr->ifr_addr;
struct epoch_tracker et;
struct ifaddr *ifa;
struct in_ifaddr *ia;
int error;
if (ifp == NULL)
return (EADDRNOTAVAIL);
/*
* Filter out 4 ioctls we implement directly. Forward the rest
* to specific functions and ifp->if_ioctl().
*/
switch (cmd) {
case SIOCGIFADDR:
case SIOCGIFBRDADDR:
case SIOCGIFDSTADDR:
case SIOCGIFNETMASK:
break;
case SIOCGIFALIAS:
sx_xlock(&in_control_sx);
error = in_gifaddr_ioctl(cmd, data, ifp, td);
sx_xunlock(&in_control_sx);
return (error);
case SIOCDIFADDR:
sx_xlock(&in_control_sx);
error = in_difaddr_ioctl(cmd, data, ifp, td);
sx_xunlock(&in_control_sx);
return (error);
case OSIOCAIFADDR: /* 9.x compat */
case SIOCAIFADDR:
sx_xlock(&in_control_sx);
error = in_aifaddr_ioctl(cmd, data, ifp, td);
sx_xunlock(&in_control_sx);
return (error);
case SIOCSIFADDR:
case SIOCSIFBRDADDR:
case SIOCSIFDSTADDR:
case SIOCSIFNETMASK:
/* We no longer support that old commands. */
return (EINVAL);
default:
if (ifp->if_ioctl == NULL)
return (EOPNOTSUPP);
return ((*ifp->if_ioctl)(ifp, cmd, data));
}
if (addr->sin_addr.s_addr != INADDR_ANY &&
prison_check_ip4(td->td_ucred, &addr->sin_addr) != 0)
return (EADDRNOTAVAIL);
/*
* Find address for this interface, if it exists. If an
* address was specified, find that one instead of the
* first one on the interface, if possible.
*/
NET_EPOCH_ENTER(et);
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family != AF_INET)
continue;
ia = (struct in_ifaddr *)ifa;
if (ia->ia_addr.sin_addr.s_addr == addr->sin_addr.s_addr)
break;
}
if (ifa == NULL)
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link)
if (ifa->ifa_addr->sa_family == AF_INET) {
ia = (struct in_ifaddr *)ifa;
if (prison_check_ip4(td->td_ucred,
&ia->ia_addr.sin_addr) == 0)
break;
}
if (ifa == NULL) {
NET_EPOCH_EXIT(et);
return (EADDRNOTAVAIL);
}
error = 0;
switch (cmd) {
case SIOCGIFADDR:
*addr = ia->ia_addr;
break;
case SIOCGIFBRDADDR:
if ((ifp->if_flags & IFF_BROADCAST) == 0) {
error = EINVAL;
break;
}
*addr = ia->ia_broadaddr;
break;
case SIOCGIFDSTADDR:
if ((ifp->if_flags & IFF_POINTOPOINT) == 0) {
error = EINVAL;
break;
}
*addr = ia->ia_dstaddr;
break;
case SIOCGIFNETMASK:
*addr = ia->ia_sockmask;
break;
}
NET_EPOCH_EXIT(et);
return (error);
}
static int
in_aifaddr_ioctl(u_long cmd, caddr_t data, struct ifnet *ifp, struct thread *td)
{
const struct in_aliasreq *ifra = (struct in_aliasreq *)data;
const struct sockaddr_in *addr = &ifra->ifra_addr;
const struct sockaddr_in *broadaddr = &ifra->ifra_broadaddr;
const struct sockaddr_in *mask = &ifra->ifra_mask;
const struct sockaddr_in *dstaddr = &ifra->ifra_dstaddr;
const int vhid = (cmd == SIOCAIFADDR) ? ifra->ifra_vhid : 0;
struct epoch_tracker et;
struct ifaddr *ifa;
struct in_ifaddr *ia;
bool iaIsFirst;
int error = 0;
error = priv_check(td, PRIV_NET_ADDIFADDR);
if (error)
return (error);
/*
* ifra_addr must be present and be of INET family.
* ifra_broadaddr/ifra_dstaddr and ifra_mask are optional.
*/
if (addr->sin_len != sizeof(struct sockaddr_in) ||
addr->sin_family != AF_INET)
return (EINVAL);
if (broadaddr->sin_len != 0 &&
(broadaddr->sin_len != sizeof(struct sockaddr_in) ||
broadaddr->sin_family != AF_INET))
return (EINVAL);
if (mask->sin_len != 0 &&
(mask->sin_len != sizeof(struct sockaddr_in) ||
mask->sin_family != AF_INET))
return (EINVAL);
if ((ifp->if_flags & IFF_POINTOPOINT) &&
(dstaddr->sin_len != sizeof(struct sockaddr_in) ||
dstaddr->sin_addr.s_addr == INADDR_ANY))
return (EDESTADDRREQ);
if (vhid > 0 && carp_attach_p == NULL)
return (EPROTONOSUPPORT);
/*
* See whether address already exist.
*/
iaIsFirst = true;
ia = NULL;
NET_EPOCH_ENTER(et);
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
struct in_ifaddr *it;
if (ifa->ifa_addr->sa_family != AF_INET)
continue;
it = (struct in_ifaddr *)ifa;
if (it->ia_addr.sin_addr.s_addr == addr->sin_addr.s_addr &&
prison_check_ip4(td->td_ucred, &addr->sin_addr) == 0)
ia = it;
else
iaIsFirst = false;
}
NET_EPOCH_EXIT(et);
if (ia != NULL)
(void )in_difaddr_ioctl(cmd, data, ifp, td);
ifa = ifa_alloc(sizeof(struct in_ifaddr), M_WAITOK);
ia = (struct in_ifaddr *)ifa;
ifa->ifa_addr = (struct sockaddr *)&ia->ia_addr;
ifa->ifa_dstaddr = (struct sockaddr *)&ia->ia_dstaddr;
ifa->ifa_netmask = (struct sockaddr *)&ia->ia_sockmask;
callout_init_rw(&ia->ia_garp_timer, &ifp->if_addr_lock,
CALLOUT_RETURNUNLOCKED);
ia->ia_ifp = ifp;
ia->ia_addr = *addr;
if (mask->sin_len != 0) {
ia->ia_sockmask = *mask;
ia->ia_subnetmask = ntohl(ia->ia_sockmask.sin_addr.s_addr);
} else {
in_addr_t i = ntohl(addr->sin_addr.s_addr);
/*
* Be compatible with network classes, if netmask isn't
* supplied, guess it based on classes.
*/
if (IN_CLASSA(i))
ia->ia_subnetmask = IN_CLASSA_NET;
else if (IN_CLASSB(i))
ia->ia_subnetmask = IN_CLASSB_NET;
else
ia->ia_subnetmask = IN_CLASSC_NET;
ia->ia_sockmask.sin_addr.s_addr = htonl(ia->ia_subnetmask);
}
ia->ia_subnet = ntohl(addr->sin_addr.s_addr) & ia->ia_subnetmask;
in_socktrim(&ia->ia_sockmask);
if (ifp->if_flags & IFF_BROADCAST) {
if (broadaddr->sin_len != 0) {
ia->ia_broadaddr = *broadaddr;
} else if (ia->ia_subnetmask == IN_RFC3021_MASK) {
ia->ia_broadaddr.sin_addr.s_addr = INADDR_BROADCAST;
ia->ia_broadaddr.sin_len = sizeof(struct sockaddr_in);
ia->ia_broadaddr.sin_family = AF_INET;
} else {
ia->ia_broadaddr.sin_addr.s_addr =
htonl(ia->ia_subnet | ~ia->ia_subnetmask);
ia->ia_broadaddr.sin_len = sizeof(struct sockaddr_in);
ia->ia_broadaddr.sin_family = AF_INET;
}
}
if (ifp->if_flags & IFF_POINTOPOINT)
ia->ia_dstaddr = *dstaddr;
/* XXXGL: rtinit() needs this strange assignment. */
if (ifp->if_flags & IFF_LOOPBACK)
ia->ia_dstaddr = ia->ia_addr;
if (vhid != 0) {
error = (*carp_attach_p)(&ia->ia_ifa, vhid);
if (error)
return (error);
}
/* if_addrhead is already referenced by ifa_alloc() */
IF_ADDR_WLOCK(ifp);
CK_STAILQ_INSERT_TAIL(&ifp->if_addrhead, ifa, ifa_link);
IF_ADDR_WUNLOCK(ifp);
ifa_ref(ifa); /* in_ifaddrhead */
IN_IFADDR_WLOCK();
CK_STAILQ_INSERT_TAIL(&V_in_ifaddrhead, ia, ia_link);
LIST_INSERT_HEAD(INADDR_HASH(ia->ia_addr.sin_addr.s_addr), ia, ia_hash);
IN_IFADDR_WUNLOCK();
/*
* Give the interface a chance to initialize
* if this is its first address,
* and to validate the address if necessary.
*/
if (ifp->if_ioctl != NULL) {
error = (*ifp->if_ioctl)(ifp, SIOCSIFADDR, (caddr_t)ia);
if (error)
goto fail1;
}
/*
* Add route for the network.
*/
if (vhid == 0) {
int flags = RTF_UP;
if (ifp->if_flags & (IFF_LOOPBACK|IFF_POINTOPOINT))
flags |= RTF_HOST;
error = in_addprefix(ia, flags);
if (error)
goto fail1;
}
/*
* Add a loopback route to self.
*/
if (vhid == 0 && (ifp->if_flags & IFF_LOOPBACK) == 0 &&
ia->ia_addr.sin_addr.s_addr != INADDR_ANY &&
!((ifp->if_flags & IFF_POINTOPOINT) &&
ia->ia_dstaddr.sin_addr.s_addr == ia->ia_addr.sin_addr.s_addr)) {
struct in_ifaddr *eia;
eia = in_localip_more(ia);
if (eia == NULL) {
error = ifa_add_loopback_route((struct ifaddr *)ia,
(struct sockaddr *)&ia->ia_addr);
if (error)
goto fail2;
} else
ifa_free(&eia->ia_ifa);
}
if (iaIsFirst && (ifp->if_flags & IFF_MULTICAST)) {
struct in_addr allhosts_addr;
struct in_ifinfo *ii;
ii = ((struct in_ifinfo *)ifp->if_afdata[AF_INET]);
allhosts_addr.s_addr = htonl(INADDR_ALLHOSTS_GROUP);
error = in_joingroup(ifp, &allhosts_addr, NULL,
&ii->ii_allhosts);
}
/*
* Note: we don't need extra reference for ifa, since we called
* with sx lock held, and ifaddr can not be deleted in concurrent
* thread.
*/
EVENTHANDLER_INVOKE(ifaddr_event_ext, ifp, ifa, IFADDR_EVENT_ADD);
return (error);
fail2:
if (vhid == 0)
(void )in_scrubprefix(ia, LLE_STATIC);
fail1:
if (ia->ia_ifa.ifa_carp)
(*carp_detach_p)(&ia->ia_ifa, false);
IF_ADDR_WLOCK(ifp);
CK_STAILQ_REMOVE(&ifp->if_addrhead, &ia->ia_ifa, ifaddr, ifa_link);
IF_ADDR_WUNLOCK(ifp);
ifa_free(&ia->ia_ifa); /* if_addrhead */
IN_IFADDR_WLOCK();
CK_STAILQ_REMOVE(&V_in_ifaddrhead, ia, in_ifaddr, ia_link);
LIST_REMOVE(ia, ia_hash);
IN_IFADDR_WUNLOCK();
ifa_free(&ia->ia_ifa); /* in_ifaddrhead */
return (error);
}
static int
in_difaddr_ioctl(u_long cmd, caddr_t data, struct ifnet *ifp, struct thread *td)
{
const struct ifreq *ifr = (struct ifreq *)data;
const struct sockaddr_in *addr = (const struct sockaddr_in *)
&ifr->ifr_addr;
struct ifaddr *ifa;
struct in_ifaddr *ia;
bool deleteAny, iaIsLast;
int error;
if (td != NULL) {
error = priv_check(td, PRIV_NET_DELIFADDR);
if (error)
return (error);
}
if (addr->sin_len != sizeof(struct sockaddr_in) ||
addr->sin_family != AF_INET)
deleteAny = true;
else
deleteAny = false;
iaIsLast = true;
ia = NULL;
IF_ADDR_WLOCK(ifp);
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
struct in_ifaddr *it;
if (ifa->ifa_addr->sa_family != AF_INET)
continue;
it = (struct in_ifaddr *)ifa;
if (deleteAny && ia == NULL && (td == NULL ||
prison_check_ip4(td->td_ucred, &it->ia_addr.sin_addr) == 0))
ia = it;
if (it->ia_addr.sin_addr.s_addr == addr->sin_addr.s_addr &&
(td == NULL || prison_check_ip4(td->td_ucred,
&addr->sin_addr) == 0))
ia = it;
if (it != ia)
iaIsLast = false;
}
if (ia == NULL) {
IF_ADDR_WUNLOCK(ifp);
return (EADDRNOTAVAIL);
}
CK_STAILQ_REMOVE(&ifp->if_addrhead, &ia->ia_ifa, ifaddr, ifa_link);
IF_ADDR_WUNLOCK(ifp);
ifa_free(&ia->ia_ifa); /* if_addrhead */
IN_IFADDR_WLOCK();
CK_STAILQ_REMOVE(&V_in_ifaddrhead, ia, in_ifaddr, ia_link);
LIST_REMOVE(ia, ia_hash);
IN_IFADDR_WUNLOCK();
/*
* in_scrubprefix() kills the interface route.
*/
in_scrubprefix(ia, LLE_STATIC);
/*
* in_ifadown gets rid of all the rest of
* the routes. This is not quite the right
* thing to do, but at least if we are running
* a routing process they will come back.
*/
in_ifadown(&ia->ia_ifa, 1);
if (ia->ia_ifa.ifa_carp)
(*carp_detach_p)(&ia->ia_ifa, cmd == SIOCAIFADDR);
/*
* If this is the last IPv4 address configured on this
* interface, leave the all-hosts group.
* No state-change report need be transmitted.
*/
if (iaIsLast && (ifp->if_flags & IFF_MULTICAST)) {
struct in_ifinfo *ii;
ii = ((struct in_ifinfo *)ifp->if_afdata[AF_INET]);
if (ii->ii_allhosts) {
(void)in_leavegroup(ii->ii_allhosts, NULL);
ii->ii_allhosts = NULL;
}
}
IF_ADDR_WLOCK(ifp);
if (callout_stop(&ia->ia_garp_timer) == 1) {
ifa_free(&ia->ia_ifa);
}
IF_ADDR_WUNLOCK(ifp);
EVENTHANDLER_INVOKE(ifaddr_event_ext, ifp, &ia->ia_ifa,
IFADDR_EVENT_DEL);
ifa_free(&ia->ia_ifa); /* in_ifaddrhead */
return (0);
}
static int
in_gifaddr_ioctl(u_long cmd, caddr_t data, struct ifnet *ifp, struct thread *td)
{
struct in_aliasreq *ifra = (struct in_aliasreq *)data;
const struct sockaddr_in *addr = &ifra->ifra_addr;
struct epoch_tracker et;
struct ifaddr *ifa;
struct in_ifaddr *ia;
/*
* ifra_addr must be present and be of INET family.
*/
if (addr->sin_len != sizeof(struct sockaddr_in) ||
addr->sin_family != AF_INET)
return (EINVAL);
/*
* See whether address exist.
*/
ia = NULL;
NET_EPOCH_ENTER(et);
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
struct in_ifaddr *it;
if (ifa->ifa_addr->sa_family != AF_INET)
continue;
it = (struct in_ifaddr *)ifa;
if (it->ia_addr.sin_addr.s_addr == addr->sin_addr.s_addr &&
prison_check_ip4(td->td_ucred, &addr->sin_addr) == 0) {
ia = it;
break;
}
}
if (ia == NULL) {
NET_EPOCH_EXIT(et);
return (EADDRNOTAVAIL);
}
ifra->ifra_mask = ia->ia_sockmask;
if ((ifp->if_flags & IFF_POINTOPOINT) &&
ia->ia_dstaddr.sin_family == AF_INET)
ifra->ifra_dstaddr = ia->ia_dstaddr;
else if ((ifp->if_flags & IFF_BROADCAST) &&
ia->ia_broadaddr.sin_family == AF_INET)
ifra->ifra_broadaddr = ia->ia_broadaddr;
else
memset(&ifra->ifra_broadaddr, 0,
sizeof(ifra->ifra_broadaddr));
NET_EPOCH_EXIT(et);
return (0);
}
+static int
+in_match_ifaddr(const struct rtentry *rt, const struct nhop_object *nh, void *arg)
+{
+
+ if (nh->nh_ifa == (struct ifaddr *)arg)
+ return (1);
+
+ return (0);
+}
+
+static int
+in_handle_prefix_route(uint32_t fibnum, int cmd,
+ struct sockaddr_in *dst, struct sockaddr_in *netmask, struct ifaddr *ifa)
+{
+
+ NET_EPOCH_ASSERT();
+
+ /* Prepare gateway */
+ struct sockaddr_dl_short sdl = {
+ .sdl_family = AF_LINK,
+ .sdl_len = sizeof(struct sockaddr_dl_short),
+ .sdl_type = ifa->ifa_ifp->if_type,
+ .sdl_index = ifa->ifa_ifp->if_index,
+ };
+
+ struct rt_addrinfo info = {
+ .rti_ifa = ifa,
+ .rti_flags = RTF_PINNED | ((netmask != NULL) ? 0 : RTF_HOST),
+ .rti_info = {
+ [RTAX_DST] = (struct sockaddr *)dst,
+ [RTAX_NETMASK] = (struct sockaddr *)netmask,
+ [RTAX_GATEWAY] = (struct sockaddr *)&sdl,
+ },
+ /* Ensure we delete the prefix IFF prefix ifa matches */
+ .rti_filter = in_match_ifaddr,
+ .rti_filterdata = ifa,
+ };
+
+ return (rib_handle_ifaddr_info(fibnum, cmd, &info));
+}
+
+/*
+ * Adds or delete interface route corresponding to @ifa.
+ * There can be multiple options:
+ * 1) Adding addr with prefix on non-p2p/non-lo interface.
+ * Example: 192.0.2.1/24. Action: add route towards
+ * 192.0.2.0/24 via this interface, using ifa as an address source.
+ * Note: route to 192.0.2.1 will be installed separately via
+ * ifa_maintain_loopback_route().
+ * 2) Adding addr with "host" mask.
+ * Example: 192.0.2.2/32. In this case no action is performed,
+ * as the route should be installed by ifa_maintain_loopback_route().
+ * Returns 0 to indicate success.
+ * 3) Adding address with or without prefix to p2p interface.
+ * Example: 10.0.0.1/24->10.0.0.2. In this case, all other addresses
+ * covered by prefix, does not make sense in the context of p2p link.
+ * Action: add route towards 10.0.0.2 via this interface, using ifa as an
+ * address source.
+ * Similar to (1), route to 10.0.0.1 will be installed by
+ * ifa_maintain_loopback_route().
+ * 4) Adding address with or without prefix to loopback interface.
+ * Example: 192.0.2.1/24. In this case, trafic to non-host addresses cannot
+ * be forwarded, as it would introduce an infinite cycle.
+ * Similar to (2), perform no action and return 0. Loopback route
+ * will be installed by ifa_maintain_loopback_route().
+ */
+int
+in_handle_ifaddr_route(int cmd, struct in_ifaddr *ia)
+{
+ struct ifaddr *ifa = &ia->ia_ifa;
+ struct in_addr daddr, maddr;
+ struct sockaddr_in *pmask;
+ struct epoch_tracker et;
+ int error;
+
+ /* Case 4: ignore loopbacks */
+ if (ifa->ifa_ifp->if_flags & IFF_LOOPBACK)
+ return (0);
+
+ if (ifa->ifa_ifp->if_flags & IFF_POINTOPOINT) {
+ /* Case 3: install route towards dst addr */
+ daddr = ia->ia_dstaddr.sin_addr;
+ pmask = NULL;
+ maddr.s_addr = INADDR_BROADCAST;
+ } else {
+ daddr = ia->ia_addr.sin_addr;
+ pmask = &ia->ia_sockmask;
+ maddr = pmask->sin_addr;
+
+ if (maddr.s_addr == INADDR_BROADCAST) {
+ /* Case 2: ignore /32 routes */
+ return (0);
+ }
+ }
+
+ struct sockaddr_in mask = {
+ .sin_family = AF_INET,
+ .sin_len = sizeof(struct sockaddr_in),
+ .sin_addr = maddr,
+ };
+
+ if (pmask != NULL)
+ pmask = &mask;
+
+ struct sockaddr_in dst = {
+ .sin_family = AF_INET,
+ .sin_len = sizeof(struct sockaddr_in),
+ .sin_addr.s_addr = daddr.s_addr & maddr.s_addr,
+ };
+
+ uint32_t fibnum = ifa->ifa_ifp->if_fib;
+ NET_EPOCH_ENTER(et);
+ error = in_handle_prefix_route(fibnum, cmd, &dst, pmask, ifa);
+ NET_EPOCH_EXIT(et);
+
+ return (error);
+}
+
+
#define rtinitflags(x) \
((((x)->ia_ifp->if_flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) != 0) \
? RTF_HOST : 0)
/*
* Check if we have a route for the given prefix already.
*/
static bool
in_hasrtprefix(struct in_ifaddr *target, int flags)
{
struct rm_priotracker in_ifa_tracker;
struct in_ifaddr *ia;
struct in_addr prefix, mask, p, m;
bool result = false;
if ((flags & RTF_HOST) != 0) {
prefix = target->ia_dstaddr.sin_addr;
mask.s_addr = 0;
} else {
prefix = target->ia_addr.sin_addr;
mask = target->ia_sockmask.sin_addr;
prefix.s_addr &= mask.s_addr;
}
IN_IFADDR_RLOCK(&in_ifa_tracker);
/* Look for an existing address with the same prefix, mask, and fib */
CK_STAILQ_FOREACH(ia, &V_in_ifaddrhead, ia_link) {
if (rtinitflags(ia)) {
p = ia->ia_dstaddr.sin_addr;
if (prefix.s_addr != p.s_addr)
continue;
} else {
p = ia->ia_addr.sin_addr;
m = ia->ia_sockmask.sin_addr;
p.s_addr &= m.s_addr;
if (prefix.s_addr != p.s_addr ||
mask.s_addr != m.s_addr)
continue;
}
if (target->ia_ifp->if_fib != ia->ia_ifp->if_fib)
continue;
/*
* If we got a matching prefix route inserted by other
* interface address, we are done here.
*/
if (ia->ia_flags & IFA_ROUTE) {
result = true;
break;
}
}
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
return (result);
}
int
in_addprefix(struct in_ifaddr *target, int flags)
{
int error;
if (in_hasrtprefix(target, flags)) {
if (V_nosameprefix)
return (EEXIST);
else {
rt_addrmsg(RTM_ADD, &target->ia_ifa,
target->ia_ifp->if_fib);
return (0);
}
}
/*
* No-one seem to have this prefix route, so we try to insert it.
*/
- error = rtinit(&target->ia_ifa, (int)RTM_ADD, flags);
+ rt_addrmsg(RTM_ADD, &target->ia_ifa, target->ia_ifp->if_fib);
+ error = in_handle_ifaddr_route(RTM_ADD, target);
if (!error)
target->ia_flags |= IFA_ROUTE;
return (error);
}
/*
* Removes either all lle entries for given @ia, or lle
* corresponding to @ia address.
*/
static void
in_scrubprefixlle(struct in_ifaddr *ia, int all, u_int flags)
{
struct sockaddr_in addr, mask;
struct sockaddr *saddr, *smask;
struct ifnet *ifp;
saddr = (struct sockaddr *)&addr;
bzero(&addr, sizeof(addr));
addr.sin_len = sizeof(addr);
addr.sin_family = AF_INET;
smask = (struct sockaddr *)&mask;
bzero(&mask, sizeof(mask));
mask.sin_len = sizeof(mask);
mask.sin_family = AF_INET;
mask.sin_addr.s_addr = ia->ia_subnetmask;
ifp = ia->ia_ifp;
if (all) {
/*
* Remove all L2 entries matching given prefix.
* Convert address to host representation to avoid
* doing this on every callback. ia_subnetmask is already
* stored in host representation.
*/
addr.sin_addr.s_addr = ntohl(ia->ia_addr.sin_addr.s_addr);
lltable_prefix_free(AF_INET, saddr, smask, flags);
} else {
/* Remove interface address only */
addr.sin_addr.s_addr = ia->ia_addr.sin_addr.s_addr;
lltable_delete_addr(LLTABLE(ifp), LLE_IFADDR, saddr);
}
}
/*
* If there is no other address in the system that can serve a route to the
* same prefix, remove the route. Hand over the route to the new address
* otherwise.
*/
int
in_scrubprefix(struct in_ifaddr *target, u_int flags)
{
struct rm_priotracker in_ifa_tracker;
struct in_ifaddr *ia;
struct in_addr prefix, mask, p, m;
int error = 0;
/*
* Remove the loopback route to the interface address.
*/
if ((target->ia_addr.sin_addr.s_addr != INADDR_ANY) &&
!(target->ia_ifp->if_flags & IFF_LOOPBACK) &&
(flags & LLE_STATIC)) {
struct in_ifaddr *eia;
/*
* XXXME: add fib-aware in_localip.
* We definitely don't want to switch between
* prefixes in different fibs.
*/
eia = in_localip_more(target);
if (eia != NULL) {
error = ifa_switch_loopback_route((struct ifaddr *)eia,
(struct sockaddr *)&target->ia_addr);
ifa_free(&eia->ia_ifa);
} else {
error = ifa_del_loopback_route((struct ifaddr *)target,
(struct sockaddr *)&target->ia_addr);
}
}
if (rtinitflags(target)) {
prefix = target->ia_dstaddr.sin_addr;
mask.s_addr = 0;
} else {
prefix = target->ia_addr.sin_addr;
mask = target->ia_sockmask.sin_addr;
prefix.s_addr &= mask.s_addr;
}
if ((target->ia_flags & IFA_ROUTE) == 0) {
rt_addrmsg(RTM_DELETE, &target->ia_ifa, target->ia_ifp->if_fib);
/*
* Removing address from !IFF_UP interface or
* prefix which exists on other interface (along with route).
* No entries should exist here except target addr.
* Given that, delete this entry only.
*/
in_scrubprefixlle(target, 0, flags);
return (0);
}
IN_IFADDR_RLOCK(&in_ifa_tracker);
CK_STAILQ_FOREACH(ia, &V_in_ifaddrhead, ia_link) {
if (rtinitflags(ia)) {
p = ia->ia_dstaddr.sin_addr;
if (prefix.s_addr != p.s_addr)
continue;
} else {
p = ia->ia_addr.sin_addr;
m = ia->ia_sockmask.sin_addr;
p.s_addr &= m.s_addr;
if (prefix.s_addr != p.s_addr ||
mask.s_addr != m.s_addr)
continue;
}
if ((ia->ia_ifp->if_flags & IFF_UP) == 0)
continue;
/*
* If we got a matching prefix address, move IFA_ROUTE and
* the route itself to it. Make sure that routing daemons
* get a heads-up.
*/
if ((ia->ia_flags & IFA_ROUTE) == 0) {
ifa_ref(&ia->ia_ifa);
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
- error = rtinit(&(target->ia_ifa), (int)RTM_DELETE,
- rtinitflags(target));
+ error = in_handle_ifaddr_route(RTM_DELETE, target);
if (error == 0)
target->ia_flags &= ~IFA_ROUTE;
else
log(LOG_INFO, "in_scrubprefix: err=%d, old prefix delete failed\n",
error);
/* Scrub all entries IFF interface is different */
in_scrubprefixlle(target, target->ia_ifp != ia->ia_ifp,
flags);
- error = rtinit(&ia->ia_ifa, (int)RTM_ADD,
- rtinitflags(ia) | RTF_UP);
+ error = in_handle_ifaddr_route(RTM_ADD, ia);
if (error == 0)
ia->ia_flags |= IFA_ROUTE;
else
log(LOG_INFO, "in_scrubprefix: err=%d, new prefix add failed\n",
error);
ifa_free(&ia->ia_ifa);
return (error);
}
}
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
/*
* remove all L2 entries on the given prefix
*/
in_scrubprefixlle(target, 1, flags);
/*
* As no-one seem to have this prefix, we can remove the route.
*/
- error = rtinit(&(target->ia_ifa), (int)RTM_DELETE, rtinitflags(target));
+ rt_addrmsg(RTM_DELETE, &target->ia_ifa, target->ia_ifp->if_fib);
+ error = in_handle_ifaddr_route(RTM_DELETE, target);
if (error == 0)
target->ia_flags &= ~IFA_ROUTE;
else
log(LOG_INFO, "in_scrubprefix: err=%d, prefix delete failed\n", error);
return (error);
}
#undef rtinitflags
void
in_ifscrub_all(void)
{
struct ifnet *ifp;
struct ifaddr *ifa, *nifa;
struct ifaliasreq ifr;
IFNET_RLOCK();
CK_STAILQ_FOREACH(ifp, &V_ifnet, if_link) {
/* Cannot lock here - lock recursion. */
/* NET_EPOCH_ENTER(et); */
CK_STAILQ_FOREACH_SAFE(ifa, &ifp->if_addrhead, ifa_link, nifa) {
if (ifa->ifa_addr->sa_family != AF_INET)
continue;
/*
* This is ugly but the only way for legacy IP to
* cleanly remove addresses and everything attached.
*/
bzero(&ifr, sizeof(ifr));
ifr.ifra_addr = *ifa->ifa_addr;
if (ifa->ifa_dstaddr)
ifr.ifra_broadaddr = *ifa->ifa_dstaddr;
(void)in_control(NULL, SIOCDIFADDR, (caddr_t)&ifr,
ifp, NULL);
}
/* NET_EPOCH_EXIT(et); */
in_purgemaddrs(ifp);
igmp_domifdetach(ifp);
}
IFNET_RUNLOCK();
}
int
in_ifaddr_broadcast(struct in_addr in, struct in_ifaddr *ia)
{
return ((in.s_addr == ia->ia_broadaddr.sin_addr.s_addr ||
/*
* Check for old-style (host 0) broadcast, but
* taking into account that RFC 3021 obsoletes it.
*/
(ia->ia_subnetmask != IN_RFC3021_MASK &&
ntohl(in.s_addr) == ia->ia_subnet)) &&
/*
* Check for an all one subnetmask. These
* only exist when an interface gets a secondary
* address.
*/
ia->ia_subnetmask != (u_long)0xffffffff);
}
/*
* Return 1 if the address might be a local broadcast address.
*/
int
in_broadcast(struct in_addr in, struct ifnet *ifp)
{
struct ifaddr *ifa;
int found;
NET_EPOCH_ASSERT();
if (in.s_addr == INADDR_BROADCAST ||
in.s_addr == INADDR_ANY)
return (1);
if ((ifp->if_flags & IFF_BROADCAST) == 0)
return (0);
found = 0;
/*
* Look through the list of addresses for a match
* with a broadcast address.
*/
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link)
if (ifa->ifa_addr->sa_family == AF_INET &&
in_ifaddr_broadcast(in, (struct in_ifaddr *)ifa)) {
found = 1;
break;
}
return (found);
}
/*
* On interface removal, clean up IPv4 data structures hung off of the ifnet.
*/
void
in_ifdetach(struct ifnet *ifp)
{
IN_MULTI_LOCK();
in_pcbpurgeif0(&V_ripcbinfo, ifp);
in_pcbpurgeif0(&V_udbinfo, ifp);
in_pcbpurgeif0(&V_ulitecbinfo, ifp);
in_purgemaddrs(ifp);
IN_MULTI_UNLOCK();
/*
* Make sure all multicast deletions invoking if_ioctl() are
* completed before returning. Else we risk accessing a freed
* ifnet structure pointer.
*/
inm_release_wait(NULL);
}
/*
* Delete all IPv4 multicast address records, and associated link-layer
* multicast address records, associated with ifp.
* XXX It looks like domifdetach runs AFTER the link layer cleanup.
* XXX This should not race with ifma_protospec being set during
* a new allocation, if it does, we have bigger problems.
*/
static void
in_purgemaddrs(struct ifnet *ifp)
{
struct in_multi_head purgeinms;
struct in_multi *inm;
struct ifmultiaddr *ifma, *next;
SLIST_INIT(&purgeinms);
IN_MULTI_LIST_LOCK();
/*
* Extract list of in_multi associated with the detaching ifp
* which the PF_INET layer is about to release.
* We need to do this as IF_ADDR_LOCK() may be re-acquired
* by code further down.
*/
IF_ADDR_WLOCK(ifp);
restart:
CK_STAILQ_FOREACH_SAFE(ifma, &ifp->if_multiaddrs, ifma_link, next) {
if (ifma->ifma_addr->sa_family != AF_INET ||
ifma->ifma_protospec == NULL)
continue;
inm = (struct in_multi *)ifma->ifma_protospec;
inm_rele_locked(&purgeinms, inm);
if (__predict_false(ifma_restart)) {
ifma_restart = true;
goto restart;
}
}
IF_ADDR_WUNLOCK(ifp);
inm_release_list_deferred(&purgeinms);
igmp_ifdetach(ifp);
IN_MULTI_LIST_UNLOCK();
}
struct in_llentry {
struct llentry base;
};
#define IN_LLTBL_DEFAULT_HSIZE 32
#define IN_LLTBL_HASH(k, h) \
(((((((k >> 8) ^ k) >> 8) ^ k) >> 8) ^ k) & ((h) - 1))
/*
* Do actual deallocation of @lle.
*/
static void
in_lltable_destroy_lle_unlocked(epoch_context_t ctx)
{
struct llentry *lle;
lle = __containerof(ctx, struct llentry, lle_epoch_ctx);
LLE_LOCK_DESTROY(lle);
LLE_REQ_DESTROY(lle);
free(lle, M_LLTABLE);
}
/*
* Called by the datapath to indicate that
* the entry was used.
*/
static void
in_lltable_mark_used(struct llentry *lle)
{
LLE_REQ_LOCK(lle);
lle->r_skip_req = 0;
LLE_REQ_UNLOCK(lle);
}
/*
* Called by LLE_FREE_LOCKED when number of references
* drops to zero.
*/
static void
in_lltable_destroy_lle(struct llentry *lle)
{
LLE_WUNLOCK(lle);
NET_EPOCH_CALL(in_lltable_destroy_lle_unlocked, &lle->lle_epoch_ctx);
}
static struct llentry *
in_lltable_new(struct in_addr addr4, u_int flags)
{
struct in_llentry *lle;
lle = malloc(sizeof(struct in_llentry), M_LLTABLE, M_NOWAIT | M_ZERO);
if (lle == NULL) /* NB: caller generates msg */
return NULL;
/*
* For IPv4 this will trigger "arpresolve" to generate
* an ARP request.
*/
lle->base.la_expire = time_uptime; /* mark expired */
lle->base.r_l3addr.addr4 = addr4;
lle->base.lle_refcnt = 1;
lle->base.lle_free = in_lltable_destroy_lle;
LLE_LOCK_INIT(&lle->base);
LLE_REQ_INIT(&lle->base);
callout_init(&lle->base.lle_timer, 1);
return (&lle->base);
}
#define IN_ARE_MASKED_ADDR_EQUAL(d, a, m) ( \
((((d).s_addr ^ (a).s_addr) & (m).s_addr)) == 0 )
static int
in_lltable_match_prefix(const struct sockaddr *saddr,
const struct sockaddr *smask, u_int flags, struct llentry *lle)
{
struct in_addr addr, mask, lle_addr;
addr = ((const struct sockaddr_in *)saddr)->sin_addr;
mask = ((const struct sockaddr_in *)smask)->sin_addr;
lle_addr.s_addr = ntohl(lle->r_l3addr.addr4.s_addr);
if (IN_ARE_MASKED_ADDR_EQUAL(lle_addr, addr, mask) == 0)
return (0);
if (lle->la_flags & LLE_IFADDR) {
/*
* Delete LLE_IFADDR records IFF address & flag matches.
* Note that addr is the interface address within prefix
* being matched.
* Note also we should handle 'ifdown' cases without removing
* ifaddr macs.
*/
if (addr.s_addr == lle_addr.s_addr && (flags & LLE_STATIC) != 0)
return (1);
return (0);
}
/* flags & LLE_STATIC means deleting both dynamic and static entries */
if ((flags & LLE_STATIC) || !(lle->la_flags & LLE_STATIC))
return (1);
return (0);
}
static void
in_lltable_free_entry(struct lltable *llt, struct llentry *lle)
{
size_t pkts_dropped;
LLE_WLOCK_ASSERT(lle);
KASSERT(llt != NULL, ("lltable is NULL"));
/* Unlink entry from table if not already */
if ((lle->la_flags & LLE_LINKED) != 0) {
IF_AFDATA_WLOCK_ASSERT(llt->llt_ifp);
lltable_unlink_entry(llt, lle);
}
/* Drop hold queue */
pkts_dropped = llentry_free(lle);
ARPSTAT_ADD(dropped, pkts_dropped);
}
static int
in_lltable_rtcheck(struct ifnet *ifp, u_int flags, const struct sockaddr *l3addr)
{
struct rt_addrinfo info;
struct sockaddr_in rt_key, rt_mask;
struct sockaddr rt_gateway;
int rt_flags;
KASSERT(l3addr->sa_family == AF_INET,
("sin_family %d", l3addr->sa_family));
bzero(&rt_key, sizeof(rt_key));
rt_key.sin_len = sizeof(rt_key);
bzero(&rt_mask, sizeof(rt_mask));
rt_mask.sin_len = sizeof(rt_mask);
bzero(&rt_gateway, sizeof(rt_gateway));
rt_gateway.sa_len = sizeof(rt_gateway);
bzero(&info, sizeof(info));
info.rti_info[RTAX_DST] = (struct sockaddr *)&rt_key;
info.rti_info[RTAX_NETMASK] = (struct sockaddr *)&rt_mask;
info.rti_info[RTAX_GATEWAY] = (struct sockaddr *)&rt_gateway;
if (rib_lookup_info(ifp->if_fib, l3addr, NHR_REF, 0, &info) != 0)
return (EINVAL);
rt_flags = info.rti_flags;
/*
* If the gateway for an existing host route matches the target L3
* address, which is a special route inserted by some implementation
* such as MANET, and the interface is of the correct type, then
* allow for ARP to proceed.
*/
if (rt_flags & RTF_GATEWAY) {
if (!(rt_flags & RTF_HOST) || !info.rti_ifp ||
info.rti_ifp->if_type != IFT_ETHER ||
(info.rti_ifp->if_flags & (IFF_NOARP | IFF_STATICARP)) != 0 ||
memcmp(rt_gateway.sa_data, l3addr->sa_data,
sizeof(in_addr_t)) != 0) {
rib_free_info(&info);
return (EINVAL);
}
}
rib_free_info(&info);
/*
* Make sure that at least the destination address is covered
* by the route. This is for handling the case where 2 or more
* interfaces have the same prefix. An incoming packet arrives
* on one interface and the corresponding outgoing packet leaves
* another interface.
*/
if (!(rt_flags & RTF_HOST) && info.rti_ifp != ifp) {
const char *sa, *mask, *addr, *lim;
const struct sockaddr_in *l3sin;
mask = (const char *)&rt_mask;
/*
* Just being extra cautious to avoid some custom
* code getting into trouble.
*/
if ((info.rti_addrs & RTA_NETMASK) == 0)
return (EINVAL);
sa = (const char *)&rt_key;
addr = (const char *)l3addr;
l3sin = (const struct sockaddr_in *)l3addr;
lim = addr + l3sin->sin_len;
for ( ; addr < lim; sa++, mask++, addr++) {
if ((*sa ^ *addr) & *mask) {
#ifdef DIAGNOSTIC
char addrbuf[INET_ADDRSTRLEN];
log(LOG_INFO, "IPv4 address: \"%s\" "
"is not on the network\n",
inet_ntoa_r(l3sin->sin_addr, addrbuf));
#endif
return (EINVAL);
}
}
}
return (0);
}
static inline uint32_t
in_lltable_hash_dst(const struct in_addr dst, uint32_t hsize)
{
return (IN_LLTBL_HASH(dst.s_addr, hsize));
}
static uint32_t
in_lltable_hash(const struct llentry *lle, uint32_t hsize)
{
return (in_lltable_hash_dst(lle->r_l3addr.addr4, hsize));
}
static void
in_lltable_fill_sa_entry(const struct llentry *lle, struct sockaddr *sa)
{
struct sockaddr_in *sin;
sin = (struct sockaddr_in *)sa;
bzero(sin, sizeof(*sin));
sin->sin_family = AF_INET;
sin->sin_len = sizeof(*sin);
sin->sin_addr = lle->r_l3addr.addr4;
}
static inline struct llentry *
in_lltable_find_dst(struct lltable *llt, struct in_addr dst)
{
struct llentry *lle;
struct llentries *lleh;
u_int hashidx;
hashidx = in_lltable_hash_dst(dst, llt->llt_hsize);
lleh = &llt->lle_head[hashidx];
CK_LIST_FOREACH(lle, lleh, lle_next) {
if (lle->la_flags & LLE_DELETED)
continue;
if (lle->r_l3addr.addr4.s_addr == dst.s_addr)
break;
}
return (lle);
}
static void
in_lltable_delete_entry(struct lltable *llt, struct llentry *lle)
{
lle->la_flags |= LLE_DELETED;
EVENTHANDLER_INVOKE(lle_event, lle, LLENTRY_DELETED);
#ifdef DIAGNOSTIC
log(LOG_INFO, "ifaddr cache = %p is deleted\n", lle);
#endif
llentry_free(lle);
}
static struct llentry *
in_lltable_alloc(struct lltable *llt, u_int flags, const struct sockaddr *l3addr)
{
const struct sockaddr_in *sin = (const struct sockaddr_in *)l3addr;
struct ifnet *ifp = llt->llt_ifp;
struct llentry *lle;
char linkhdr[LLE_MAX_LINKHDR];
size_t linkhdrsize;
int lladdr_off;
KASSERT(l3addr->sa_family == AF_INET,
("sin_family %d", l3addr->sa_family));
/*
* A route that covers the given address must have
* been installed 1st because we are doing a resolution,
* verify this.
*/
if (!(flags & LLE_IFADDR) &&
in_lltable_rtcheck(ifp, flags, l3addr) != 0)
return (NULL);
lle = in_lltable_new(sin->sin_addr, flags);
if (lle == NULL) {
log(LOG_INFO, "lla_lookup: new lle malloc failed\n");
return (NULL);
}
lle->la_flags = flags;
if (flags & LLE_STATIC)
lle->r_flags |= RLLE_VALID;
if ((flags & LLE_IFADDR) == LLE_IFADDR) {
linkhdrsize = LLE_MAX_LINKHDR;
if (lltable_calc_llheader(ifp, AF_INET, IF_LLADDR(ifp),
linkhdr, &linkhdrsize, &lladdr_off) != 0) {
NET_EPOCH_CALL(in_lltable_destroy_lle_unlocked, &lle->lle_epoch_ctx);
return (NULL);
}
lltable_set_entry_addr(ifp, lle, linkhdr, linkhdrsize,
lladdr_off);
lle->la_flags |= LLE_STATIC;
lle->r_flags |= (RLLE_VALID | RLLE_IFADDR);
}
return (lle);
}
/*
* Return NULL if not found or marked for deletion.
* If found return lle read locked.
*/
static struct llentry *
in_lltable_lookup(struct lltable *llt, u_int flags, const struct sockaddr *l3addr)
{
const struct sockaddr_in *sin = (const struct sockaddr_in *)l3addr;
struct llentry *lle;
IF_AFDATA_LOCK_ASSERT(llt->llt_ifp);
KASSERT(l3addr->sa_family == AF_INET,
("sin_family %d", l3addr->sa_family));
KASSERT((flags & (LLE_UNLOCKED | LLE_EXCLUSIVE)) !=
(LLE_UNLOCKED | LLE_EXCLUSIVE),
("wrong lle request flags: %#x", flags));
lle = in_lltable_find_dst(llt, sin->sin_addr);
if (lle == NULL)
return (NULL);
if (flags & LLE_UNLOCKED)
return (lle);
if (flags & LLE_EXCLUSIVE)
LLE_WLOCK(lle);
else
LLE_RLOCK(lle);
/*
* If the afdata lock is not held, the LLE may have been unlinked while
* we were blocked on the LLE lock. Check for this case.
*/
if (__predict_false((lle->la_flags & LLE_LINKED) == 0)) {
if (flags & LLE_EXCLUSIVE)
LLE_WUNLOCK(lle);
else
LLE_RUNLOCK(lle);
return (NULL);
}
return (lle);
}
static int
in_lltable_dump_entry(struct lltable *llt, struct llentry *lle,
struct sysctl_req *wr)
{
struct ifnet *ifp = llt->llt_ifp;
/* XXX stack use */
struct {
struct rt_msghdr rtm;
struct sockaddr_in sin;
struct sockaddr_dl sdl;
} arpc;
struct sockaddr_dl *sdl;
int error;
bzero(&arpc, sizeof(arpc));
/* skip deleted entries */
if ((lle->la_flags & LLE_DELETED) == LLE_DELETED)
return (0);
/* Skip if jailed and not a valid IP of the prison. */
lltable_fill_sa_entry(lle,(struct sockaddr *)&arpc.sin);
if (prison_if(wr->td->td_ucred, (struct sockaddr *)&arpc.sin) != 0)
return (0);
/*
* produce a msg made of:
* struct rt_msghdr;
* struct sockaddr_in; (IPv4)
* struct sockaddr_dl;
*/
arpc.rtm.rtm_msglen = sizeof(arpc);
arpc.rtm.rtm_version = RTM_VERSION;
arpc.rtm.rtm_type = RTM_GET;
arpc.rtm.rtm_flags = RTF_UP;
arpc.rtm.rtm_addrs = RTA_DST | RTA_GATEWAY;
/* publish */
if (lle->la_flags & LLE_PUB)
arpc.rtm.rtm_flags |= RTF_ANNOUNCE;
sdl = &arpc.sdl;
sdl->sdl_family = AF_LINK;
sdl->sdl_len = sizeof(*sdl);
sdl->sdl_index = ifp->if_index;
sdl->sdl_type = ifp->if_type;
if ((lle->la_flags & LLE_VALID) == LLE_VALID) {
sdl->sdl_alen = ifp->if_addrlen;
bcopy(lle->ll_addr, LLADDR(sdl), ifp->if_addrlen);
} else {
sdl->sdl_alen = 0;
bzero(LLADDR(sdl), ifp->if_addrlen);
}
arpc.rtm.rtm_rmx.rmx_expire =
lle->la_flags & LLE_STATIC ? 0 : lle->la_expire;
arpc.rtm.rtm_flags |= (RTF_HOST | RTF_LLDATA);
if (lle->la_flags & LLE_STATIC)
arpc.rtm.rtm_flags |= RTF_STATIC;
if (lle->la_flags & LLE_IFADDR)
arpc.rtm.rtm_flags |= RTF_PINNED;
arpc.rtm.rtm_index = ifp->if_index;
error = SYSCTL_OUT(wr, &arpc, sizeof(arpc));
return (error);
}
static struct lltable *
in_lltattach(struct ifnet *ifp)
{
struct lltable *llt;
llt = lltable_allocate_htbl(IN_LLTBL_DEFAULT_HSIZE);
llt->llt_af = AF_INET;
llt->llt_ifp = ifp;
llt->llt_lookup = in_lltable_lookup;
llt->llt_alloc_entry = in_lltable_alloc;
llt->llt_delete_entry = in_lltable_delete_entry;
llt->llt_dump_entry = in_lltable_dump_entry;
llt->llt_hash = in_lltable_hash;
llt->llt_fill_sa_entry = in_lltable_fill_sa_entry;
llt->llt_free_entry = in_lltable_free_entry;
llt->llt_match_prefix = in_lltable_match_prefix;
llt->llt_mark_used = in_lltable_mark_used;
lltable_link(llt);
return (llt);
}
void *
in_domifattach(struct ifnet *ifp)
{
struct in_ifinfo *ii;
ii = malloc(sizeof(struct in_ifinfo), M_IFADDR, M_WAITOK|M_ZERO);
ii->ii_llt = in_lltattach(ifp);
ii->ii_igmp = igmp_domifattach(ifp);
return (ii);
}
void
in_domifdetach(struct ifnet *ifp, void *aux)
{
struct in_ifinfo *ii = (struct in_ifinfo *)aux;
igmp_domifdetach(ifp);
lltable_free(ii->ii_llt);
free(ii, M_IFADDR);
}
diff --git a/sys/netinet/in_var.h b/sys/netinet/in_var.h
index fabd8e1ab50c..3a83c5e832ab 100644
--- a/sys/netinet/in_var.h
+++ b/sys/netinet/in_var.h
@@ -1,483 +1,484 @@
/*-
* SPDX-License-Identifier: BSD-3-Clause
*
* Copyright (c) 1985, 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.
*
* @(#)in_var.h 8.2 (Berkeley) 1/9/95
* $FreeBSD$
*/
#ifndef _NETINET_IN_VAR_H_
#define _NETINET_IN_VAR_H_
/*
* Argument structure for SIOCAIFADDR.
*/
struct in_aliasreq {
char ifra_name[IFNAMSIZ]; /* if name, e.g. "en0" */
struct sockaddr_in ifra_addr;
struct sockaddr_in ifra_broadaddr;
#define ifra_dstaddr ifra_broadaddr
struct sockaddr_in ifra_mask;
int ifra_vhid;
};
#ifdef _KERNEL
#include <sys/queue.h>
#include <sys/fnv_hash.h>
#include <sys/tree.h>
struct igmp_ifsoftc;
struct in_multi;
struct lltable;
SLIST_HEAD(in_multi_head, in_multi);
/*
* IPv4 per-interface state.
*/
struct in_ifinfo {
struct lltable *ii_llt; /* ARP state */
struct igmp_ifsoftc *ii_igmp; /* IGMP state */
struct in_multi *ii_allhosts; /* 224.0.0.1 membership */
};
/*
* Interface address, Internet version. One of these structures
* is allocated for each Internet address on an interface.
* The ifaddr structure contains the protocol-independent part
* of the structure and is assumed to be first.
*/
struct in_ifaddr {
struct ifaddr ia_ifa; /* protocol-independent info */
#define ia_ifp ia_ifa.ifa_ifp
#define ia_flags ia_ifa.ifa_flags
/* ia_subnet{,mask} in host order */
u_long ia_subnet; /* subnet address */
u_long ia_subnetmask; /* mask of subnet */
LIST_ENTRY(in_ifaddr) ia_hash; /* entry in bucket of inet addresses */
CK_STAILQ_ENTRY(in_ifaddr) ia_link; /* list of internet addresses */
struct sockaddr_in ia_addr; /* reserve space for interface name */
struct sockaddr_in ia_dstaddr; /* reserve space for broadcast addr */
#define ia_broadaddr ia_dstaddr
struct sockaddr_in ia_sockmask; /* reserve space for general netmask */
struct callout ia_garp_timer; /* timer for retransmitting GARPs */
int ia_garp_count; /* count of retransmitted GARPs */
};
/*
* Given a pointer to an in_ifaddr (ifaddr),
* return a pointer to the addr as a sockaddr_in.
*/
#define IA_SIN(ia) (&(((struct in_ifaddr *)(ia))->ia_addr))
#define IA_DSTSIN(ia) (&(((struct in_ifaddr *)(ia))->ia_dstaddr))
#define IA_MASKSIN(ia) (&(((struct in_ifaddr *)(ia))->ia_sockmask))
#define IN_LNAOF(in, ifa) \
((ntohl((in).s_addr) & ~((struct in_ifaddr *)(ifa)->ia_subnetmask))
extern u_char inetctlerrmap[];
#define LLTABLE(ifp) \
((struct in_ifinfo *)(ifp)->if_afdata[AF_INET])->ii_llt
/*
* Hash table for IP addresses.
*/
CK_STAILQ_HEAD(in_ifaddrhead, in_ifaddr);
LIST_HEAD(in_ifaddrhashhead, in_ifaddr);
VNET_DECLARE(struct in_ifaddrhashhead *, in_ifaddrhashtbl);
VNET_DECLARE(struct in_ifaddrhead, in_ifaddrhead);
VNET_DECLARE(u_long, in_ifaddrhmask); /* mask for hash table */
#define V_in_ifaddrhashtbl VNET(in_ifaddrhashtbl)
#define V_in_ifaddrhead VNET(in_ifaddrhead)
#define V_in_ifaddrhmask VNET(in_ifaddrhmask)
#define INADDR_NHASH_LOG2 9
#define INADDR_NHASH (1 << INADDR_NHASH_LOG2)
#define INADDR_HASHVAL(x) fnv_32_buf((&(x)), sizeof(x), FNV1_32_INIT)
#define INADDR_HASH(x) \
(&V_in_ifaddrhashtbl[INADDR_HASHVAL(x) & V_in_ifaddrhmask])
extern struct rmlock in_ifaddr_lock;
#define IN_IFADDR_LOCK_ASSERT() rm_assert(&in_ifaddr_lock, RA_LOCKED)
#define IN_IFADDR_RLOCK(t) rm_rlock(&in_ifaddr_lock, (t))
#define IN_IFADDR_RLOCK_ASSERT() rm_assert(&in_ifaddr_lock, RA_RLOCKED)
#define IN_IFADDR_RUNLOCK(t) rm_runlock(&in_ifaddr_lock, (t))
#define IN_IFADDR_WLOCK() rm_wlock(&in_ifaddr_lock)
#define IN_IFADDR_WLOCK_ASSERT() rm_assert(&in_ifaddr_lock, RA_WLOCKED)
#define IN_IFADDR_WUNLOCK() rm_wunlock(&in_ifaddr_lock)
/*
* Macro for finding the internet address structure (in_ifaddr)
* corresponding to one of our IP addresses (in_addr).
*/
#define INADDR_TO_IFADDR(addr, ia) \
/* struct in_addr addr; */ \
/* struct in_ifaddr *ia; */ \
do { \
\
LIST_FOREACH(ia, INADDR_HASH((addr).s_addr), ia_hash) \
if (IA_SIN(ia)->sin_addr.s_addr == (addr).s_addr) \
break; \
} while (0)
/*
* Macro for finding the interface (ifnet structure) corresponding to one
* of our IP addresses.
*/
#define INADDR_TO_IFP(addr, ifp) \
/* struct in_addr addr; */ \
/* struct ifnet *ifp; */ \
{ \
struct in_ifaddr *ia; \
\
INADDR_TO_IFADDR(addr, ia); \
(ifp) = (ia == NULL) ? NULL : ia->ia_ifp; \
}
/*
* Macro for finding the internet address structure (in_ifaddr) corresponding
* to a given interface (ifnet structure).
*/
#define IFP_TO_IA(ifp, ia, t) \
/* struct ifnet *ifp; */ \
/* struct in_ifaddr *ia; */ \
/* struct rm_priotracker *t; */ \
do { \
NET_EPOCH_ASSERT(); \
IN_IFADDR_RLOCK((t)); \
for ((ia) = CK_STAILQ_FIRST(&V_in_ifaddrhead); \
(ia) != NULL && (ia)->ia_ifp != (ifp); \
(ia) = CK_STAILQ_NEXT((ia), ia_link)) \
continue; \
IN_IFADDR_RUNLOCK((t)); \
} while (0)
/*
* Legacy IPv4 IGMP per-link structure.
*/
struct router_info {
struct ifnet *rti_ifp;
int rti_type; /* type of router which is querier on this interface */
int rti_time; /* # of slow timeouts since last old query */
SLIST_ENTRY(router_info) rti_list;
};
/*
* IPv4 multicast IGMP-layer source entry.
*/
struct ip_msource {
RB_ENTRY(ip_msource) ims_link; /* RB tree links */
in_addr_t ims_haddr; /* host byte order */
struct ims_st {
uint16_t ex; /* # of exclusive members */
uint16_t in; /* # of inclusive members */
} ims_st[2]; /* state at t0, t1 */
uint8_t ims_stp; /* pending query */
};
/*
* IPv4 multicast PCB-layer source entry.
*/
struct in_msource {
RB_ENTRY(ip_msource) ims_link; /* RB tree links */
in_addr_t ims_haddr; /* host byte order */
uint8_t imsl_st[2]; /* state before/at commit */
};
RB_HEAD(ip_msource_tree, ip_msource); /* define struct ip_msource_tree */
static __inline int
ip_msource_cmp(const struct ip_msource *a, const struct ip_msource *b)
{
if (a->ims_haddr < b->ims_haddr)
return (-1);
if (a->ims_haddr == b->ims_haddr)
return (0);
return (1);
}
RB_PROTOTYPE(ip_msource_tree, ip_msource, ims_link, ip_msource_cmp);
/*
* IPv4 multicast PCB-layer group filter descriptor.
*/
struct in_mfilter {
struct ip_msource_tree imf_sources; /* source list for (S,G) */
u_long imf_nsrc; /* # of source entries */
uint8_t imf_st[2]; /* state before/at commit */
struct in_multi *imf_inm; /* associated multicast address */
STAILQ_ENTRY(in_mfilter) imf_entry; /* list entry */
};
/*
* Helper types and functions for IPv4 multicast filters.
*/
STAILQ_HEAD(ip_mfilter_head, in_mfilter);
struct in_mfilter *ip_mfilter_alloc(int mflags, int st0, int st1);
void ip_mfilter_free(struct in_mfilter *);
static inline void
ip_mfilter_init(struct ip_mfilter_head *head)
{
STAILQ_INIT(head);
}
static inline struct in_mfilter *
ip_mfilter_first(const struct ip_mfilter_head *head)
{
return (STAILQ_FIRST(head));
}
static inline void
ip_mfilter_insert(struct ip_mfilter_head *head, struct in_mfilter *imf)
{
STAILQ_INSERT_TAIL(head, imf, imf_entry);
}
static inline void
ip_mfilter_remove(struct ip_mfilter_head *head, struct in_mfilter *imf)
{
STAILQ_REMOVE(head, imf, in_mfilter, imf_entry);
}
#define IP_MFILTER_FOREACH(imf, head) \
STAILQ_FOREACH(imf, head, imf_entry)
static inline size_t
ip_mfilter_count(struct ip_mfilter_head *head)
{
struct in_mfilter *imf;
size_t num = 0;
STAILQ_FOREACH(imf, head, imf_entry)
num++;
return (num);
}
/*
* IPv4 group descriptor.
*
* For every entry on an ifnet's if_multiaddrs list which represents
* an IP multicast group, there is one of these structures.
*
* If any source filters are present, then a node will exist in the RB-tree
* to permit fast lookup by source whenever an operation takes place.
* This permits pre-order traversal when we issue reports.
* Source filter trees are kept separately from the socket layer to
* greatly simplify locking.
*
* When IGMPv3 is active, inm_timer is the response to group query timer.
* The state-change timer inm_sctimer is separate; whenever state changes
* for the group the state change record is generated and transmitted,
* and kept if retransmissions are necessary.
*
* FUTURE: inm_link is now only used when groups are being purged
* on a detaching ifnet. It could be demoted to a SLIST_ENTRY, but
* because it is at the very start of the struct, we can't do this
* w/o breaking the ABI for ifmcstat.
*/
struct in_multi {
LIST_ENTRY(in_multi) inm_link; /* to-be-released by in_ifdetach */
struct in_addr inm_addr; /* IP multicast address, convenience */
struct ifnet *inm_ifp; /* back pointer to ifnet */
struct ifmultiaddr *inm_ifma; /* back pointer to ifmultiaddr */
u_int inm_timer; /* IGMPv1/v2 group / v3 query timer */
u_int inm_state; /* state of the membership */
void *inm_rti; /* unused, legacy field */
u_int inm_refcount; /* reference count */
/* New fields for IGMPv3 follow. */
struct igmp_ifsoftc *inm_igi; /* IGMP info */
SLIST_ENTRY(in_multi) inm_nrele; /* to-be-released by IGMP */
struct ip_msource_tree inm_srcs; /* tree of sources */
u_long inm_nsrc; /* # of tree entries */
struct mbufq inm_scq; /* queue of pending
* state-change packets */
struct timeval inm_lastgsrtv; /* Time of last G-S-R query */
uint16_t inm_sctimer; /* state-change timer */
uint16_t inm_scrv; /* state-change rexmit count */
/*
* SSM state counters which track state at T0 (the time the last
* state-change report's RV timer went to zero) and T1
* (time of pending report, i.e. now).
* Used for computing IGMPv3 state-change reports. Several refcounts
* are maintained here to optimize for common use-cases.
*/
struct inm_st {
uint16_t iss_fmode; /* IGMP filter mode */
uint16_t iss_asm; /* # of ASM listeners */
uint16_t iss_ex; /* # of exclusive members */
uint16_t iss_in; /* # of inclusive members */
uint16_t iss_rec; /* # of recorded sources */
} inm_st[2]; /* state at t0, t1 */
};
/*
* Helper function to derive the filter mode on a source entry
* from its internal counters. Predicates are:
* A source is only excluded if all listeners exclude it.
* A source is only included if no listeners exclude it,
* and at least one listener includes it.
* May be used by ifmcstat(8).
*/
static __inline uint8_t
ims_get_mode(const struct in_multi *inm, const struct ip_msource *ims,
uint8_t t)
{
t = !!t;
if (inm->inm_st[t].iss_ex > 0 &&
inm->inm_st[t].iss_ex == ims->ims_st[t].ex)
return (MCAST_EXCLUDE);
else if (ims->ims_st[t].in > 0 && ims->ims_st[t].ex == 0)
return (MCAST_INCLUDE);
return (MCAST_UNDEFINED);
}
#ifdef SYSCTL_DECL
SYSCTL_DECL(_net_inet);
SYSCTL_DECL(_net_inet_ip);
SYSCTL_DECL(_net_inet_raw);
#endif
/*
* Lock macros for IPv4 layer multicast address lists. IPv4 lock goes
* before link layer multicast locks in the lock order. In most cases,
* consumers of IN_*_MULTI() macros should acquire the locks before
* calling them; users of the in_{add,del}multi() functions should not.
*/
extern struct mtx in_multi_list_mtx;
extern struct sx in_multi_sx;
#define IN_MULTI_LIST_LOCK() mtx_lock(&in_multi_list_mtx)
#define IN_MULTI_LIST_UNLOCK() mtx_unlock(&in_multi_list_mtx)
#define IN_MULTI_LIST_LOCK_ASSERT() mtx_assert(&in_multi_list_mtx, MA_OWNED)
#define IN_MULTI_LIST_UNLOCK_ASSERT() mtx_assert(&in_multi_list_mtx, MA_NOTOWNED)
#define IN_MULTI_LOCK() sx_xlock(&in_multi_sx)
#define IN_MULTI_UNLOCK() sx_xunlock(&in_multi_sx)
#define IN_MULTI_LOCK_ASSERT() sx_assert(&in_multi_sx, SA_XLOCKED)
#define IN_MULTI_UNLOCK_ASSERT() sx_assert(&in_multi_sx, SA_XUNLOCKED)
void inm_disconnect(struct in_multi *inm);
extern int ifma_restart;
/* Acquire an in_multi record. */
static __inline void
inm_acquire_locked(struct in_multi *inm)
{
IN_MULTI_LIST_LOCK_ASSERT();
++inm->inm_refcount;
}
static __inline void
inm_acquire(struct in_multi *inm)
{
IN_MULTI_LIST_LOCK();
inm_acquire_locked(inm);
IN_MULTI_LIST_UNLOCK();
}
static __inline void
inm_rele_locked(struct in_multi_head *inmh, struct in_multi *inm)
{
MPASS(inm->inm_refcount > 0);
IN_MULTI_LIST_LOCK_ASSERT();
if (--inm->inm_refcount == 0) {
MPASS(inmh != NULL);
inm_disconnect(inm);
inm->inm_ifma->ifma_protospec = NULL;
SLIST_INSERT_HEAD(inmh, inm, inm_nrele);
}
}
/*
* Return values for imo_multi_filter().
*/
#define MCAST_PASS 0 /* Pass */
#define MCAST_NOTGMEMBER 1 /* This host not a member of group */
#define MCAST_NOTSMEMBER 2 /* This host excluded source */
#define MCAST_MUTED 3 /* [deprecated] */
struct rib_head;
struct ip_moptions;
struct in_multi *inm_lookup_locked(struct ifnet *, const struct in_addr);
struct in_multi *inm_lookup(struct ifnet *, const struct in_addr);
int imo_multi_filter(const struct ip_moptions *, const struct ifnet *,
const struct sockaddr *, const struct sockaddr *);
void inm_commit(struct in_multi *);
void inm_clear_recorded(struct in_multi *);
void inm_print(const struct in_multi *);
int inm_record_source(struct in_multi *inm, const in_addr_t);
void inm_release_deferred(struct in_multi *);
void inm_release_list_deferred(struct in_multi_head *);
void inm_release_wait(void *);
struct in_multi *
in_addmulti(struct in_addr *, struct ifnet *);
int in_joingroup(struct ifnet *, const struct in_addr *,
/*const*/ struct in_mfilter *, struct in_multi **);
int in_joingroup_locked(struct ifnet *, const struct in_addr *,
/*const*/ struct in_mfilter *, struct in_multi **);
int in_leavegroup(struct in_multi *, /*const*/ struct in_mfilter *);
int in_leavegroup_locked(struct in_multi *,
/*const*/ struct in_mfilter *);
int in_control(struct socket *, u_long, caddr_t, struct ifnet *,
struct thread *);
int in_addprefix(struct in_ifaddr *, int);
int in_scrubprefix(struct in_ifaddr *, u_int);
void in_ifscrub_all(void);
+int in_handle_ifaddr_route(int, struct in_ifaddr *);
void ip_input(struct mbuf *);
void ip_direct_input(struct mbuf *);
void in_ifadown(struct ifaddr *ifa, int);
struct mbuf *ip_tryforward(struct mbuf *);
void *in_domifattach(struct ifnet *);
void in_domifdetach(struct ifnet *, void *);
struct rib_head *in_inithead(uint32_t fibnum);
#ifdef VIMAGE
void in_detachhead(struct rib_head *rh);
#endif
#endif /* _KERNEL */
/* INET6 stuff */
#include <netinet6/in6_var.h>
#endif /* _NETINET_IN_VAR_H_ */
diff --git a/sys/netinet/raw_ip.c b/sys/netinet/raw_ip.c
index a63fc19587f9..c9def015343c 100644
--- a/sys/netinet/raw_ip.c
+++ b/sys/netinet/raw_ip.c
@@ -1,1183 +1,1185 @@
/*-
* SPDX-License-Identifier: BSD-3-Clause
*
* Copyright (c) 1982, 1986, 1988, 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.
*
* @(#)raw_ip.c 8.7 (Berkeley) 5/15/95
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_inet.h"
#include "opt_inet6.h"
#include "opt_ipsec.h"
#include "opt_route.h"
#include <sys/param.h>
#include <sys/jail.h>
#include <sys/kernel.h>
#include <sys/eventhandler.h>
#include <sys/lock.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/protosw.h>
#include <sys/rmlock.h>
#include <sys/rwlock.h>
#include <sys/signalvar.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sx.h>
#include <sys/sysctl.h>
#include <sys/systm.h>
#include <vm/uma.h>
#include <net/if.h>
#include <net/if_var.h>
#include <net/route.h>
+#include <net/route/route_ctl.h>
#include <net/vnet.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/in_fib.h>
#include <netinet/in_pcb.h>
#include <netinet/in_var.h>
#include <netinet/if_ether.h>
#include <netinet/ip.h>
#include <netinet/ip_var.h>
#include <netinet/ip_mroute.h>
#include <netinet/ip_icmp.h>
#include <netipsec/ipsec_support.h>
#include <machine/stdarg.h>
#include <security/mac/mac_framework.h>
VNET_DEFINE(int, ip_defttl) = IPDEFTTL;
SYSCTL_INT(_net_inet_ip, IPCTL_DEFTTL, ttl, CTLFLAG_VNET | CTLFLAG_RW,
&VNET_NAME(ip_defttl), 0,
"Maximum TTL on IP packets");
VNET_DEFINE(struct inpcbhead, ripcb);
VNET_DEFINE(struct inpcbinfo, ripcbinfo);
#define V_ripcb VNET(ripcb)
#define V_ripcbinfo VNET(ripcbinfo)
/*
* Control and data hooks for ipfw, dummynet, divert and so on.
* The data hooks are not used here but it is convenient
* to keep them all in one place.
*/
VNET_DEFINE(ip_fw_chk_ptr_t, ip_fw_chk_ptr) = NULL;
VNET_DEFINE(ip_fw_ctl_ptr_t, ip_fw_ctl_ptr) = NULL;
int (*ip_dn_ctl_ptr)(struct sockopt *);
int (*ip_dn_io_ptr)(struct mbuf **, struct ip_fw_args *);
void (*ip_divert_ptr)(struct mbuf *, bool);
int (*ng_ipfw_input_p)(struct mbuf **, struct ip_fw_args *, bool);
#ifdef INET
/*
* Hooks for multicast routing. They all default to NULL, so leave them not
* initialized and rely on BSS being set to 0.
*/
/*
* The socket used to communicate with the multicast routing daemon.
*/
VNET_DEFINE(struct socket *, ip_mrouter);
/*
* The various mrouter and rsvp functions.
*/
int (*ip_mrouter_set)(struct socket *, struct sockopt *);
int (*ip_mrouter_get)(struct socket *, struct sockopt *);
int (*ip_mrouter_done)(void);
int (*ip_mforward)(struct ip *, struct ifnet *, struct mbuf *,
struct ip_moptions *);
int (*mrt_ioctl)(u_long, caddr_t, int);
int (*legal_vif_num)(int);
u_long (*ip_mcast_src)(int);
int (*rsvp_input_p)(struct mbuf **, int *, int);
int (*ip_rsvp_vif)(struct socket *, struct sockopt *);
void (*ip_rsvp_force_done)(struct socket *);
#endif /* INET */
extern struct protosw inetsw[];
u_long rip_sendspace = 9216;
SYSCTL_ULONG(_net_inet_raw, OID_AUTO, maxdgram, CTLFLAG_RW,
&rip_sendspace, 0, "Maximum outgoing raw IP datagram size");
u_long rip_recvspace = 9216;
SYSCTL_ULONG(_net_inet_raw, OID_AUTO, recvspace, CTLFLAG_RW,
&rip_recvspace, 0, "Maximum space for incoming raw IP datagrams");
/*
* Hash functions
*/
#define INP_PCBHASH_RAW_SIZE 256
#define INP_PCBHASH_RAW(proto, laddr, faddr, mask) \
(((proto) + (laddr) + (faddr)) % (mask) + 1)
#ifdef INET
static void
rip_inshash(struct inpcb *inp)
{
struct inpcbinfo *pcbinfo = inp->inp_pcbinfo;
struct inpcbhead *pcbhash;
int hash;
INP_INFO_WLOCK_ASSERT(pcbinfo);
INP_WLOCK_ASSERT(inp);
if (inp->inp_ip_p != 0 &&
inp->inp_laddr.s_addr != INADDR_ANY &&
inp->inp_faddr.s_addr != INADDR_ANY) {
hash = INP_PCBHASH_RAW(inp->inp_ip_p, inp->inp_laddr.s_addr,
inp->inp_faddr.s_addr, pcbinfo->ipi_hashmask);
} else
hash = 0;
pcbhash = &pcbinfo->ipi_hashbase[hash];
CK_LIST_INSERT_HEAD(pcbhash, inp, inp_hash);
}
static void
rip_delhash(struct inpcb *inp)
{
INP_INFO_WLOCK_ASSERT(inp->inp_pcbinfo);
INP_WLOCK_ASSERT(inp);
CK_LIST_REMOVE(inp, inp_hash);
}
#endif /* INET */
/*
* Raw interface to IP protocol.
*/
/*
* Initialize raw connection block q.
*/
static void
rip_zone_change(void *tag)
{
uma_zone_set_max(V_ripcbinfo.ipi_zone, maxsockets);
}
static int
rip_inpcb_init(void *mem, int size, int flags)
{
struct inpcb *inp = mem;
INP_LOCK_INIT(inp, "inp", "rawinp");
return (0);
}
void
rip_init(void)
{
in_pcbinfo_init(&V_ripcbinfo, "rip", &V_ripcb, INP_PCBHASH_RAW_SIZE,
1, "ripcb", rip_inpcb_init, IPI_HASHFIELDS_NONE);
EVENTHANDLER_REGISTER(maxsockets_change, rip_zone_change, NULL,
EVENTHANDLER_PRI_ANY);
}
#ifdef VIMAGE
static void
rip_destroy(void *unused __unused)
{
in_pcbinfo_destroy(&V_ripcbinfo);
}
VNET_SYSUNINIT(raw_ip, SI_SUB_PROTO_DOMAIN, SI_ORDER_FOURTH, rip_destroy, NULL);
#endif
#ifdef INET
static int
rip_append(struct inpcb *last, struct ip *ip, struct mbuf *n,
struct sockaddr_in *ripsrc)
{
int policyfail = 0;
INP_LOCK_ASSERT(last);
#if defined(IPSEC) || defined(IPSEC_SUPPORT)
/* check AH/ESP integrity. */
if (IPSEC_ENABLED(ipv4)) {
if (IPSEC_CHECK_POLICY(ipv4, n, last) != 0)
policyfail = 1;
}
#endif /* IPSEC */
#ifdef MAC
if (!policyfail && mac_inpcb_check_deliver(last, n) != 0)
policyfail = 1;
#endif
/* Check the minimum TTL for socket. */
if (last->inp_ip_minttl && last->inp_ip_minttl > ip->ip_ttl)
policyfail = 1;
if (!policyfail) {
struct mbuf *opts = NULL;
struct socket *so;
so = last->inp_socket;
if ((last->inp_flags & INP_CONTROLOPTS) ||
(so->so_options & (SO_TIMESTAMP | SO_BINTIME)))
ip_savecontrol(last, &opts, ip, n);
SOCKBUF_LOCK(&so->so_rcv);
if (sbappendaddr_locked(&so->so_rcv,
(struct sockaddr *)ripsrc, n, opts) == 0) {
/* should notify about lost packet */
m_freem(n);
if (opts)
m_freem(opts);
SOCKBUF_UNLOCK(&so->so_rcv);
} else
sorwakeup_locked(so);
} else
m_freem(n);
return (policyfail);
}
/*
* Setup generic address and protocol structures for raw_input routine, then
* pass them along with mbuf chain.
*/
int
rip_input(struct mbuf **mp, int *offp, int proto)
{
struct ifnet *ifp;
struct mbuf *m = *mp;
struct ip *ip = mtod(m, struct ip *);
struct inpcb *inp, *last;
struct sockaddr_in ripsrc;
int hash;
NET_EPOCH_ASSERT();
*mp = NULL;
bzero(&ripsrc, sizeof(ripsrc));
ripsrc.sin_len = sizeof(ripsrc);
ripsrc.sin_family = AF_INET;
ripsrc.sin_addr = ip->ip_src;
last = NULL;
ifp = m->m_pkthdr.rcvif;
hash = INP_PCBHASH_RAW(proto, ip->ip_src.s_addr,
ip->ip_dst.s_addr, V_ripcbinfo.ipi_hashmask);
CK_LIST_FOREACH(inp, &V_ripcbinfo.ipi_hashbase[hash], inp_hash) {
if (inp->inp_ip_p != proto)
continue;
#ifdef INET6
/* XXX inp locking */
if ((inp->inp_vflag & INP_IPV4) == 0)
continue;
#endif
if (inp->inp_laddr.s_addr != ip->ip_dst.s_addr)
continue;
if (inp->inp_faddr.s_addr != ip->ip_src.s_addr)
continue;
if (last != NULL) {
struct mbuf *n;
n = m_copym(m, 0, M_COPYALL, M_NOWAIT);
if (n != NULL)
(void) rip_append(last, ip, n, &ripsrc);
/* XXX count dropped packet */
INP_RUNLOCK(last);
last = NULL;
}
INP_RLOCK(inp);
if (__predict_false(inp->inp_flags2 & INP_FREED))
goto skip_1;
if (jailed_without_vnet(inp->inp_cred)) {
/*
* XXX: If faddr was bound to multicast group,
* jailed raw socket will drop datagram.
*/
if (prison_check_ip4(inp->inp_cred, &ip->ip_dst) != 0)
goto skip_1;
}
last = inp;
continue;
skip_1:
INP_RUNLOCK(inp);
}
CK_LIST_FOREACH(inp, &V_ripcbinfo.ipi_hashbase[0], inp_hash) {
if (inp->inp_ip_p && inp->inp_ip_p != proto)
continue;
#ifdef INET6
/* XXX inp locking */
if ((inp->inp_vflag & INP_IPV4) == 0)
continue;
#endif
if (!in_nullhost(inp->inp_laddr) &&
!in_hosteq(inp->inp_laddr, ip->ip_dst))
continue;
if (!in_nullhost(inp->inp_faddr) &&
!in_hosteq(inp->inp_faddr, ip->ip_src))
continue;
if (last != NULL) {
struct mbuf *n;
n = m_copym(m, 0, M_COPYALL, M_NOWAIT);
if (n != NULL)
(void) rip_append(last, ip, n, &ripsrc);
/* XXX count dropped packet */
INP_RUNLOCK(last);
last = NULL;
}
INP_RLOCK(inp);
if (__predict_false(inp->inp_flags2 & INP_FREED))
goto skip_2;
if (jailed_without_vnet(inp->inp_cred)) {
/*
* Allow raw socket in jail to receive multicast;
* assume process had PRIV_NETINET_RAW at attach,
* and fall through into normal filter path if so.
*/
if (!IN_MULTICAST(ntohl(ip->ip_dst.s_addr)) &&
prison_check_ip4(inp->inp_cred, &ip->ip_dst) != 0)
goto skip_2;
}
/*
* If this raw socket has multicast state, and we
* have received a multicast, check if this socket
* should receive it, as multicast filtering is now
* the responsibility of the transport layer.
*/
if (inp->inp_moptions != NULL &&
IN_MULTICAST(ntohl(ip->ip_dst.s_addr))) {
/*
* If the incoming datagram is for IGMP, allow it
* through unconditionally to the raw socket.
*
* In the case of IGMPv2, we may not have explicitly
* joined the group, and may have set IFF_ALLMULTI
* on the interface. imo_multi_filter() may discard
* control traffic we actually need to see.
*
* Userland multicast routing daemons should continue
* filter the control traffic appropriately.
*/
int blocked;
blocked = MCAST_PASS;
if (proto != IPPROTO_IGMP) {
struct sockaddr_in group;
bzero(&group, sizeof(struct sockaddr_in));
group.sin_len = sizeof(struct sockaddr_in);
group.sin_family = AF_INET;
group.sin_addr = ip->ip_dst;
blocked = imo_multi_filter(inp->inp_moptions,
ifp,
(struct sockaddr *)&group,
(struct sockaddr *)&ripsrc);
}
if (blocked != MCAST_PASS) {
IPSTAT_INC(ips_notmember);
goto skip_2;
}
}
last = inp;
continue;
skip_2:
INP_RUNLOCK(inp);
}
if (last != NULL) {
if (rip_append(last, ip, m, &ripsrc) != 0)
IPSTAT_INC(ips_delivered);
INP_RUNLOCK(last);
} else {
if (inetsw[ip_protox[ip->ip_p]].pr_input == rip_input) {
IPSTAT_INC(ips_noproto);
IPSTAT_DEC(ips_delivered);
icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_PROTOCOL, 0, 0);
} else {
m_freem(m);
}
}
return (IPPROTO_DONE);
}
/*
* Generate IP header and pass packet to ip_output. Tack on options user may
* have setup with control call.
*/
int
rip_output(struct mbuf *m, struct socket *so, ...)
{
struct epoch_tracker et;
struct ip *ip;
int error;
struct inpcb *inp = sotoinpcb(so);
va_list ap;
u_long dst;
int flags = ((so->so_options & SO_DONTROUTE) ? IP_ROUTETOIF : 0) |
IP_ALLOWBROADCAST;
int cnt, hlen;
u_char opttype, optlen, *cp;
va_start(ap, so);
dst = va_arg(ap, u_long);
va_end(ap);
/*
* If the user handed us a complete IP packet, use it. Otherwise,
* allocate an mbuf for a header and fill it in.
*/
if ((inp->inp_flags & INP_HDRINCL) == 0) {
if (m->m_pkthdr.len + sizeof(struct ip) > IP_MAXPACKET) {
m_freem(m);
return(EMSGSIZE);
}
M_PREPEND(m, sizeof(struct ip), M_NOWAIT);
if (m == NULL)
return(ENOBUFS);
INP_RLOCK(inp);
ip = mtod(m, struct ip *);
ip->ip_tos = inp->inp_ip_tos;
if (inp->inp_flags & INP_DONTFRAG)
ip->ip_off = htons(IP_DF);
else
ip->ip_off = htons(0);
ip->ip_p = inp->inp_ip_p;
ip->ip_len = htons(m->m_pkthdr.len);
ip->ip_src = inp->inp_laddr;
ip->ip_dst.s_addr = dst;
#ifdef ROUTE_MPATH
if (CALC_FLOWID_OUTBOUND) {
uint32_t hash_type, hash_val;
hash_val = fib4_calc_software_hash(ip->ip_src,
ip->ip_dst, 0, 0, ip->ip_p, &hash_type);
m->m_pkthdr.flowid = hash_val;
M_HASHTYPE_SET(m, hash_type);
flags |= IP_NODEFAULTFLOWID;
}
#endif
if (jailed(inp->inp_cred)) {
/*
* prison_local_ip4() would be good enough but would
* let a source of INADDR_ANY pass, which we do not
* want to see from jails.
*/
if (ip->ip_src.s_addr == INADDR_ANY) {
NET_EPOCH_ENTER(et);
error = in_pcbladdr(inp, &ip->ip_dst,
&ip->ip_src, inp->inp_cred);
NET_EPOCH_EXIT(et);
} else {
error = prison_local_ip4(inp->inp_cred,
&ip->ip_src);
}
if (error != 0) {
INP_RUNLOCK(inp);
m_freem(m);
return (error);
}
}
ip->ip_ttl = inp->inp_ip_ttl;
} else {
if (m->m_pkthdr.len > IP_MAXPACKET) {
m_freem(m);
return(EMSGSIZE);
}
ip = mtod(m, struct ip *);
hlen = ip->ip_hl << 2;
if (m->m_len < hlen) {
m = m_pullup(m, hlen);
if (m == NULL)
return (EINVAL);
ip = mtod(m, struct ip *);
}
#ifdef ROUTE_MPATH
if (CALC_FLOWID_OUTBOUND) {
uint32_t hash_type, hash_val;
hash_val = fib4_calc_software_hash(ip->ip_dst,
ip->ip_src, 0, 0, ip->ip_p, &hash_type);
m->m_pkthdr.flowid = hash_val;
M_HASHTYPE_SET(m, hash_type);
flags |= IP_NODEFAULTFLOWID;
}
#endif
INP_RLOCK(inp);
/*
* Don't allow both user specified and setsockopt options,
* and don't allow packet length sizes that will crash.
*/
if ((hlen < sizeof (*ip))
|| ((hlen > sizeof (*ip)) && inp->inp_options)
|| (ntohs(ip->ip_len) != m->m_pkthdr.len)) {
INP_RUNLOCK(inp);
m_freem(m);
return (EINVAL);
}
error = prison_check_ip4(inp->inp_cred, &ip->ip_src);
if (error != 0) {
INP_RUNLOCK(inp);
m_freem(m);
return (error);
}
/*
* Don't allow IP options which do not have the required
* structure as specified in section 3.1 of RFC 791 on
* pages 15-23.
*/
cp = (u_char *)(ip + 1);
cnt = hlen - sizeof (struct ip);
for (; cnt > 0; cnt -= optlen, cp += optlen) {
opttype = cp[IPOPT_OPTVAL];
if (opttype == IPOPT_EOL)
break;
if (opttype == IPOPT_NOP) {
optlen = 1;
continue;
}
if (cnt < IPOPT_OLEN + sizeof(u_char)) {
INP_RUNLOCK(inp);
m_freem(m);
return (EINVAL);
}
optlen = cp[IPOPT_OLEN];
if (optlen < IPOPT_OLEN + sizeof(u_char) ||
optlen > cnt) {
INP_RUNLOCK(inp);
m_freem(m);
return (EINVAL);
}
}
/*
* This doesn't allow application to specify ID of zero,
* but we got this limitation from the beginning of history.
*/
if (ip->ip_id == 0)
ip_fillid(ip);
/*
* XXX prevent ip_output from overwriting header fields.
*/
flags |= IP_RAWOUTPUT;
IPSTAT_INC(ips_rawout);
}
if (inp->inp_flags & INP_ONESBCAST)
flags |= IP_SENDONES;
#ifdef MAC
mac_inpcb_create_mbuf(inp, m);
#endif
NET_EPOCH_ENTER(et);
error = ip_output(m, inp->inp_options, NULL, flags,
inp->inp_moptions, inp);
NET_EPOCH_EXIT(et);
INP_RUNLOCK(inp);
return (error);
}
/*
* Raw IP socket option processing.
*
* IMPORTANT NOTE regarding access control: Traditionally, raw sockets could
* only be created by a privileged process, and as such, socket option
* operations to manage system properties on any raw socket were allowed to
* take place without explicit additional access control checks. However,
* raw sockets can now also be created in jail(), and therefore explicit
* checks are now required. Likewise, raw sockets can be used by a process
* after it gives up privilege, so some caution is required. For options
* passed down to the IP layer via ip_ctloutput(), checks are assumed to be
* performed in ip_ctloutput() and therefore no check occurs here.
* Unilaterally checking priv_check() here breaks normal IP socket option
* operations on raw sockets.
*
* When adding new socket options here, make sure to add access control
* checks here as necessary.
*
* XXX-BZ inp locking?
*/
int
rip_ctloutput(struct socket *so, struct sockopt *sopt)
{
struct inpcb *inp = sotoinpcb(so);
int error, optval;
if (sopt->sopt_level != IPPROTO_IP) {
if ((sopt->sopt_level == SOL_SOCKET) &&
(sopt->sopt_name == SO_SETFIB)) {
inp->inp_inc.inc_fibnum = so->so_fibnum;
return (0);
}
return (EINVAL);
}
error = 0;
switch (sopt->sopt_dir) {
case SOPT_GET:
switch (sopt->sopt_name) {
case IP_HDRINCL:
optval = inp->inp_flags & INP_HDRINCL;
error = sooptcopyout(sopt, &optval, sizeof optval);
break;
case IP_FW3: /* generic ipfw v.3 functions */
case IP_FW_ADD: /* ADD actually returns the body... */
case IP_FW_GET:
case IP_FW_TABLE_GETSIZE:
case IP_FW_TABLE_LIST:
case IP_FW_NAT_GET_CONFIG:
case IP_FW_NAT_GET_LOG:
if (V_ip_fw_ctl_ptr != NULL)
error = V_ip_fw_ctl_ptr(sopt);
else
error = ENOPROTOOPT;
break;
case IP_DUMMYNET3: /* generic dummynet v.3 functions */
case IP_DUMMYNET_GET:
if (ip_dn_ctl_ptr != NULL)
error = ip_dn_ctl_ptr(sopt);
else
error = ENOPROTOOPT;
break ;
case MRT_INIT:
case MRT_DONE:
case MRT_ADD_VIF:
case MRT_DEL_VIF:
case MRT_ADD_MFC:
case MRT_DEL_MFC:
case MRT_VERSION:
case MRT_ASSERT:
case MRT_API_SUPPORT:
case MRT_API_CONFIG:
case MRT_ADD_BW_UPCALL:
case MRT_DEL_BW_UPCALL:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
error = ip_mrouter_get ? ip_mrouter_get(so, sopt) :
EOPNOTSUPP;
break;
default:
error = ip_ctloutput(so, sopt);
break;
}
break;
case SOPT_SET:
switch (sopt->sopt_name) {
case IP_HDRINCL:
error = sooptcopyin(sopt, &optval, sizeof optval,
sizeof optval);
if (error)
break;
if (optval)
inp->inp_flags |= INP_HDRINCL;
else
inp->inp_flags &= ~INP_HDRINCL;
break;
case IP_FW3: /* generic ipfw v.3 functions */
case IP_FW_ADD:
case IP_FW_DEL:
case IP_FW_FLUSH:
case IP_FW_ZERO:
case IP_FW_RESETLOG:
case IP_FW_TABLE_ADD:
case IP_FW_TABLE_DEL:
case IP_FW_TABLE_FLUSH:
case IP_FW_NAT_CFG:
case IP_FW_NAT_DEL:
if (V_ip_fw_ctl_ptr != NULL)
error = V_ip_fw_ctl_ptr(sopt);
else
error = ENOPROTOOPT;
break;
case IP_DUMMYNET3: /* generic dummynet v.3 functions */
case IP_DUMMYNET_CONFIGURE:
case IP_DUMMYNET_DEL:
case IP_DUMMYNET_FLUSH:
if (ip_dn_ctl_ptr != NULL)
error = ip_dn_ctl_ptr(sopt);
else
error = ENOPROTOOPT ;
break ;
case IP_RSVP_ON:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
error = ip_rsvp_init(so);
break;
case IP_RSVP_OFF:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
error = ip_rsvp_done();
break;
case IP_RSVP_VIF_ON:
case IP_RSVP_VIF_OFF:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
error = ip_rsvp_vif ?
ip_rsvp_vif(so, sopt) : EINVAL;
break;
case MRT_INIT:
case MRT_DONE:
case MRT_ADD_VIF:
case MRT_DEL_VIF:
case MRT_ADD_MFC:
case MRT_DEL_MFC:
case MRT_VERSION:
case MRT_ASSERT:
case MRT_API_SUPPORT:
case MRT_API_CONFIG:
case MRT_ADD_BW_UPCALL:
case MRT_DEL_BW_UPCALL:
error = priv_check(curthread, PRIV_NETINET_MROUTE);
if (error != 0)
return (error);
error = ip_mrouter_set ? ip_mrouter_set(so, sopt) :
EOPNOTSUPP;
break;
default:
error = ip_ctloutput(so, sopt);
break;
}
break;
}
return (error);
}
/*
* This function exists solely to receive the PRC_IFDOWN messages which are
* sent by if_down(). It looks for an ifaddr whose ifa_addr is sa, and calls
* in_ifadown() to remove all routes corresponding to that address. It also
* receives the PRC_IFUP messages from if_up() and reinstalls the interface
* routes.
*/
void
rip_ctlinput(int cmd, struct sockaddr *sa, void *vip)
{
struct rm_priotracker in_ifa_tracker;
struct in_ifaddr *ia;
struct ifnet *ifp;
int err;
int flags;
switch (cmd) {
case PRC_IFDOWN:
IN_IFADDR_RLOCK(&in_ifa_tracker);
CK_STAILQ_FOREACH(ia, &V_in_ifaddrhead, ia_link) {
if (ia->ia_ifa.ifa_addr == sa
&& (ia->ia_flags & IFA_ROUTE)) {
ifa_ref(&ia->ia_ifa);
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
/*
* in_scrubprefix() kills the interface route.
*/
in_scrubprefix(ia, 0);
/*
* in_ifadown gets rid of all the rest of the
* routes. This is not quite the right thing
* to do, but at least if we are running a
* routing process they will come back.
*/
in_ifadown(&ia->ia_ifa, 0);
ifa_free(&ia->ia_ifa);
break;
}
}
if (ia == NULL) /* If ia matched, already unlocked. */
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
break;
case PRC_IFUP:
IN_IFADDR_RLOCK(&in_ifa_tracker);
CK_STAILQ_FOREACH(ia, &V_in_ifaddrhead, ia_link) {
if (ia->ia_ifa.ifa_addr == sa)
break;
}
if (ia == NULL || (ia->ia_flags & IFA_ROUTE)) {
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
return;
}
ifa_ref(&ia->ia_ifa);
IN_IFADDR_RUNLOCK(&in_ifa_tracker);
flags = RTF_UP;
ifp = ia->ia_ifa.ifa_ifp;
if ((ifp->if_flags & IFF_LOOPBACK)
|| (ifp->if_flags & IFF_POINTOPOINT))
flags |= RTF_HOST;
err = ifa_del_loopback_route((struct ifaddr *)ia, sa);
- err = rtinit(&ia->ia_ifa, RTM_ADD, flags);
+ rt_addrmsg(RTM_ADD, &ia->ia_ifa, ia->ia_ifp->if_fib);
+ err = in_handle_ifaddr_route(RTM_ADD, ia);
if (err == 0)
ia->ia_flags |= IFA_ROUTE;
err = ifa_add_loopback_route((struct ifaddr *)ia, sa);
ifa_free(&ia->ia_ifa);
break;
}
}
static int
rip_attach(struct socket *so, int proto, struct thread *td)
{
struct inpcb *inp;
int error;
inp = sotoinpcb(so);
KASSERT(inp == NULL, ("rip_attach: inp != NULL"));
error = priv_check(td, PRIV_NETINET_RAW);
if (error)
return (error);
if (proto >= IPPROTO_MAX || proto < 0)
return EPROTONOSUPPORT;
error = soreserve(so, rip_sendspace, rip_recvspace);
if (error)
return (error);
INP_INFO_WLOCK(&V_ripcbinfo);
error = in_pcballoc(so, &V_ripcbinfo);
if (error) {
INP_INFO_WUNLOCK(&V_ripcbinfo);
return (error);
}
inp = (struct inpcb *)so->so_pcb;
inp->inp_vflag |= INP_IPV4;
inp->inp_ip_p = proto;
inp->inp_ip_ttl = V_ip_defttl;
rip_inshash(inp);
INP_INFO_WUNLOCK(&V_ripcbinfo);
INP_WUNLOCK(inp);
return (0);
}
static void
rip_detach(struct socket *so)
{
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_detach: inp == NULL"));
KASSERT(inp->inp_faddr.s_addr == INADDR_ANY,
("rip_detach: not closed"));
INP_INFO_WLOCK(&V_ripcbinfo);
INP_WLOCK(inp);
rip_delhash(inp);
if (so == V_ip_mrouter && ip_mrouter_done)
ip_mrouter_done();
if (ip_rsvp_force_done)
ip_rsvp_force_done(so);
if (so == V_ip_rsvpd)
ip_rsvp_done();
in_pcbdetach(inp);
in_pcbfree(inp);
INP_INFO_WUNLOCK(&V_ripcbinfo);
}
static void
rip_dodisconnect(struct socket *so, struct inpcb *inp)
{
struct inpcbinfo *pcbinfo;
pcbinfo = inp->inp_pcbinfo;
INP_INFO_WLOCK(pcbinfo);
INP_WLOCK(inp);
rip_delhash(inp);
inp->inp_faddr.s_addr = INADDR_ANY;
rip_inshash(inp);
SOCK_LOCK(so);
so->so_state &= ~SS_ISCONNECTED;
SOCK_UNLOCK(so);
INP_WUNLOCK(inp);
INP_INFO_WUNLOCK(pcbinfo);
}
static void
rip_abort(struct socket *so)
{
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_abort: inp == NULL"));
rip_dodisconnect(so, inp);
}
static void
rip_close(struct socket *so)
{
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_close: inp == NULL"));
rip_dodisconnect(so, inp);
}
static int
rip_disconnect(struct socket *so)
{
struct inpcb *inp;
if ((so->so_state & SS_ISCONNECTED) == 0)
return (ENOTCONN);
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_disconnect: inp == NULL"));
rip_dodisconnect(so, inp);
return (0);
}
static int
rip_bind(struct socket *so, struct sockaddr *nam, struct thread *td)
{
struct sockaddr_in *addr = (struct sockaddr_in *)nam;
struct inpcb *inp;
int error;
if (nam->sa_len != sizeof(*addr))
return (EINVAL);
error = prison_check_ip4(td->td_ucred, &addr->sin_addr);
if (error != 0)
return (error);
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_bind: inp == NULL"));
if (CK_STAILQ_EMPTY(&V_ifnet) ||
(addr->sin_family != AF_INET && addr->sin_family != AF_IMPLINK) ||
(addr->sin_addr.s_addr &&
(inp->inp_flags & INP_BINDANY) == 0 &&
ifa_ifwithaddr_check((struct sockaddr *)addr) == 0))
return (EADDRNOTAVAIL);
INP_INFO_WLOCK(&V_ripcbinfo);
INP_WLOCK(inp);
rip_delhash(inp);
inp->inp_laddr = addr->sin_addr;
rip_inshash(inp);
INP_WUNLOCK(inp);
INP_INFO_WUNLOCK(&V_ripcbinfo);
return (0);
}
static int
rip_connect(struct socket *so, struct sockaddr *nam, struct thread *td)
{
struct sockaddr_in *addr = (struct sockaddr_in *)nam;
struct inpcb *inp;
if (nam->sa_len != sizeof(*addr))
return (EINVAL);
if (CK_STAILQ_EMPTY(&V_ifnet))
return (EADDRNOTAVAIL);
if (addr->sin_family != AF_INET && addr->sin_family != AF_IMPLINK)
return (EAFNOSUPPORT);
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_connect: inp == NULL"));
INP_INFO_WLOCK(&V_ripcbinfo);
INP_WLOCK(inp);
rip_delhash(inp);
inp->inp_faddr = addr->sin_addr;
rip_inshash(inp);
soisconnected(so);
INP_WUNLOCK(inp);
INP_INFO_WUNLOCK(&V_ripcbinfo);
return (0);
}
static int
rip_shutdown(struct socket *so)
{
struct inpcb *inp;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_shutdown: inp == NULL"));
INP_WLOCK(inp);
socantsendmore(so);
INP_WUNLOCK(inp);
return (0);
}
static int
rip_send(struct socket *so, int flags, struct mbuf *m, struct sockaddr *nam,
struct mbuf *control, struct thread *td)
{
struct inpcb *inp;
u_long dst;
inp = sotoinpcb(so);
KASSERT(inp != NULL, ("rip_send: inp == NULL"));
/*
* Note: 'dst' reads below are unlocked.
*/
if (so->so_state & SS_ISCONNECTED) {
if (nam) {
m_freem(m);
return (EISCONN);
}
dst = inp->inp_faddr.s_addr; /* Unlocked read. */
} else {
if (nam == NULL) {
m_freem(m);
return (ENOTCONN);
}
dst = ((struct sockaddr_in *)nam)->sin_addr.s_addr;
}
return (rip_output(m, so, dst));
}
#endif /* INET */
static int
rip_pcblist(SYSCTL_HANDLER_ARGS)
{
struct xinpgen xig;
struct epoch_tracker et;
struct inpcb *inp;
int error;
if (req->newptr != 0)
return (EPERM);
if (req->oldptr == 0) {
int n;
n = V_ripcbinfo.ipi_count;
n += imax(n / 8, 10);
req->oldidx = 2 * (sizeof xig) + n * sizeof(struct xinpcb);
return (0);
}
if ((error = sysctl_wire_old_buffer(req, 0)) != 0)
return (error);
bzero(&xig, sizeof(xig));
xig.xig_len = sizeof xig;
xig.xig_count = V_ripcbinfo.ipi_count;
xig.xig_gen = V_ripcbinfo.ipi_gencnt;
xig.xig_sogen = so_gencnt;
error = SYSCTL_OUT(req, &xig, sizeof xig);
if (error)
return (error);
NET_EPOCH_ENTER(et);
for (inp = CK_LIST_FIRST(V_ripcbinfo.ipi_listhead);
inp != NULL;
inp = CK_LIST_NEXT(inp, inp_list)) {
INP_RLOCK(inp);
if (inp->inp_gencnt <= xig.xig_gen &&
cr_canseeinpcb(req->td->td_ucred, inp) == 0) {
struct xinpcb xi;
in_pcbtoxinpcb(inp, &xi);
INP_RUNLOCK(inp);
error = SYSCTL_OUT(req, &xi, sizeof xi);
if (error)
break;
} else
INP_RUNLOCK(inp);
}
NET_EPOCH_EXIT(et);
if (!error) {
/*
* Give the user an updated idea of our state. If the
* generation differs from what we told her before, she knows
* that something happened while we were processing this
* request, and it might be necessary to retry.
*/
xig.xig_gen = V_ripcbinfo.ipi_gencnt;
xig.xig_sogen = so_gencnt;
xig.xig_count = V_ripcbinfo.ipi_count;
error = SYSCTL_OUT(req, &xig, sizeof xig);
}
return (error);
}
SYSCTL_PROC(_net_inet_raw, OID_AUTO/*XXX*/, pcblist,
CTLTYPE_OPAQUE | CTLFLAG_RD | CTLFLAG_MPSAFE, NULL, 0,
rip_pcblist, "S,xinpcb",
"List of active raw IP sockets");
#ifdef INET
struct pr_usrreqs rip_usrreqs = {
.pru_abort = rip_abort,
.pru_attach = rip_attach,
.pru_bind = rip_bind,
.pru_connect = rip_connect,
.pru_control = in_control,
.pru_detach = rip_detach,
.pru_disconnect = rip_disconnect,
.pru_peeraddr = in_getpeeraddr,
.pru_send = rip_send,
.pru_shutdown = rip_shutdown,
.pru_sockaddr = in_getsockaddr,
.pru_sosetlabel = in_pcbsosetlabel,
.pru_close = rip_close,
};
#endif /* INET */
diff --git a/sys/netinet6/in6.c b/sys/netinet6/in6.c
index 7c572e7b833b..b42cc16cdb6f 100644
--- a/sys/netinet6/in6.c
+++ b/sys/netinet6/in6.c
@@ -1,2547 +1,2591 @@
/*-
* SPDX-License-Identifier: BSD-3-Clause
*
* 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.
*
* $KAME: in6.c,v 1.259 2002/01/21 11:37:50 keiichi Exp $
*/
/*-
* Copyright (c) 1982, 1986, 1991, 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.
*
* @(#)in.c 8.2 (Berkeley) 11/15/93
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_inet.h"
#include "opt_inet6.h"
#include <sys/param.h>
#include <sys/eventhandler.h>
#include <sys/errno.h>
#include <sys/jail.h>
#include <sys/malloc.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sockio.h>
#include <sys/systm.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/protosw.h>
#include <sys/time.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/rmlock.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>
#include <net/if.h>
#include <net/if_var.h>
#include <net/if_types.h>
#include <net/route.h>
+#include <net/route/route_ctl.h>
#include <net/route/nhop.h>
#include <net/if_dl.h>
#include <net/vnet.h>
#include <netinet/in.h>
#include <netinet/in_var.h>
#include <net/if_llatbl.h>
#include <netinet/if_ether.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/in_pcb.h>
#include <netinet/ip_carp.h>
#include <netinet/ip6.h>
#include <netinet6/ip6_var.h>
#include <netinet6/nd6.h>
#include <netinet6/mld6_var.h>
#include <netinet6/ip6_mroute.h>
#include <netinet6/in6_ifattach.h>
#include <netinet6/scope6_var.h>
#include <netinet6/in6_fib.h>
#include <netinet6/in6_pcb.h>
/*
* struct in6_ifreq and struct ifreq must be type punnable for common members
* of ifr_ifru to allow accessors to be shared.
*/
_Static_assert(offsetof(struct in6_ifreq, ifr_ifru) ==
offsetof(struct ifreq, ifr_ifru),
"struct in6_ifreq and struct ifreq are not type punnable");
VNET_DECLARE(int, icmp6_nodeinfo_oldmcprefix);
#define V_icmp6_nodeinfo_oldmcprefix VNET(icmp6_nodeinfo_oldmcprefix)
/*
* Definitions of some costant IP6 addresses.
*/
const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT;
const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT;
const struct in6_addr in6addr_nodelocal_allnodes =
IN6ADDR_NODELOCAL_ALLNODES_INIT;
const struct in6_addr in6addr_linklocal_allnodes =
IN6ADDR_LINKLOCAL_ALLNODES_INIT;
const struct in6_addr in6addr_linklocal_allrouters =
IN6ADDR_LINKLOCAL_ALLROUTERS_INIT;
const struct in6_addr in6addr_linklocal_allv2routers =
IN6ADDR_LINKLOCAL_ALLV2ROUTERS_INIT;
const struct in6_addr in6mask0 = IN6MASK0;
const struct in6_addr in6mask32 = IN6MASK32;
const struct in6_addr in6mask64 = IN6MASK64;
const struct in6_addr in6mask96 = IN6MASK96;
const struct in6_addr in6mask128 = IN6MASK128;
const struct sockaddr_in6 sa6_any =
{ sizeof(sa6_any), AF_INET6, 0, 0, IN6ADDR_ANY_INIT, 0 };
static int in6_notify_ifa(struct ifnet *, struct in6_ifaddr *,
struct in6_aliasreq *, int);
static void in6_unlink_ifa(struct in6_ifaddr *, struct ifnet *);
static int in6_validate_ifra(struct ifnet *, struct in6_aliasreq *,
struct in6_ifaddr *, int);
static struct in6_ifaddr *in6_alloc_ifa(struct ifnet *,
struct in6_aliasreq *, int flags);
static int in6_update_ifa_internal(struct ifnet *, struct in6_aliasreq *,
struct in6_ifaddr *, int, int);
static int in6_broadcast_ifa(struct ifnet *, struct in6_aliasreq *,
struct in6_ifaddr *, int);
#define ifa2ia6(ifa) ((struct in6_ifaddr *)(ifa))
#define ia62ifa(ia6) (&((ia6)->ia_ifa))
void
in6_newaddrmsg(struct in6_ifaddr *ia, int cmd)
{
struct rt_addrinfo info;
struct ifaddr *ifa;
struct sockaddr_dl gateway;
int fibnum;
ifa = &ia->ia_ifa;
/*
* Prepare info data for the host route.
* This code mimics one from ifa_maintain_loopback_route().
*/
bzero(&info, sizeof(struct rt_addrinfo));
info.rti_flags = ifa->ifa_flags | RTF_HOST | RTF_STATIC | RTF_PINNED;
info.rti_info[RTAX_DST] = ifa->ifa_addr;
info.rti_info[RTAX_GATEWAY] = (struct sockaddr *)&gateway;
link_init_sdl(ifa->ifa_ifp, (struct sockaddr *)&gateway, ifa->ifa_ifp->if_type);
if (cmd != RTM_DELETE)
info.rti_ifp = V_loif;
fibnum = ia62ifa(ia)->ifa_ifp->if_fib;
if (cmd == RTM_ADD) {
rt_addrmsg(cmd, &ia->ia_ifa, fibnum);
rt_routemsg_info(cmd, &info, fibnum);
} else if (cmd == RTM_DELETE) {
rt_routemsg_info(cmd, &info, fibnum);
rt_addrmsg(cmd, &ia->ia_ifa, fibnum);
}
}
int
in6_mask2len(struct in6_addr *mask, u_char *lim0)
{
int x = 0, y;
u_char *lim = lim0, *p;
/* ignore the scope_id part */
if (lim0 == NULL || lim0 - (u_char *)mask > sizeof(*mask))
lim = (u_char *)mask + sizeof(*mask);
for (p = (u_char *)mask; p < lim; x++, p++) {
if (*p != 0xff)
break;
}
y = 0;
if (p < lim) {
for (y = 0; y < 8; y++) {
if ((*p & (0x80 >> y)) == 0)
break;
}
}
/*
* when the limit pointer is given, do a stricter check on the
* remaining bits.
*/
if (p < lim) {
if (y != 0 && (*p & (0x00ff >> y)) != 0)
return (-1);
for (p = p + 1; p < lim; p++)
if (*p != 0)
return (-1);
}
return x * 8 + y;
}
#ifdef COMPAT_FREEBSD32
struct in6_ndifreq32 {
char ifname[IFNAMSIZ];
uint32_t ifindex;
};
#define SIOCGDEFIFACE32_IN6 _IOWR('i', 86, struct in6_ndifreq32)
#endif
int
in6_control(struct socket *so, u_long cmd, caddr_t data,
struct ifnet *ifp, struct thread *td)
{
struct in6_ifreq *ifr = (struct in6_ifreq *)data;
struct in6_ifaddr *ia = NULL;
struct in6_aliasreq *ifra = (struct in6_aliasreq *)data;
struct sockaddr_in6 *sa6;
int carp_attached = 0;
int error;
u_long ocmd = cmd;
/*
* Compat to make pre-10.x ifconfig(8) operable.
*/
if (cmd == OSIOCAIFADDR_IN6)
cmd = SIOCAIFADDR_IN6;
switch (cmd) {
case SIOCGETSGCNT_IN6:
case SIOCGETMIFCNT_IN6:
/*
* XXX mrt_ioctl has a 3rd, unused, FIB argument in route.c.
* We cannot see how that would be needed, so do not adjust the
* KPI blindly; more likely should clean up the IPv4 variant.
*/
return (mrt6_ioctl ? mrt6_ioctl(cmd, data) : EOPNOTSUPP);
}
switch (cmd) {
case SIOCAADDRCTL_POLICY:
case SIOCDADDRCTL_POLICY:
if (td != NULL) {
error = priv_check(td, PRIV_NETINET_ADDRCTRL6);
if (error)
return (error);
}
return (in6_src_ioctl(cmd, data));
}
if (ifp == NULL)
return (EOPNOTSUPP);
switch (cmd) {
case SIOCSNDFLUSH_IN6:
case SIOCSPFXFLUSH_IN6:
case SIOCSRTRFLUSH_IN6:
case SIOCSDEFIFACE_IN6:
case SIOCSIFINFO_FLAGS:
case SIOCSIFINFO_IN6:
if (td != NULL) {
error = priv_check(td, PRIV_NETINET_ND6);
if (error)
return (error);
}
/* FALLTHROUGH */
case OSIOCGIFINFO_IN6:
case SIOCGIFINFO_IN6:
case SIOCGNBRINFO_IN6:
case SIOCGDEFIFACE_IN6:
return (nd6_ioctl(cmd, data, ifp));
#ifdef COMPAT_FREEBSD32
case SIOCGDEFIFACE32_IN6:
{
struct in6_ndifreq ndif;
struct in6_ndifreq32 *ndif32;
error = nd6_ioctl(SIOCGDEFIFACE_IN6, (caddr_t)&ndif,
ifp);
if (error)
return (error);
ndif32 = (struct in6_ndifreq32 *)data;
ndif32->ifindex = ndif.ifindex;
return (0);
}
#endif
}
switch (cmd) {
case SIOCSIFPREFIX_IN6:
case SIOCDIFPREFIX_IN6:
case SIOCAIFPREFIX_IN6:
case SIOCCIFPREFIX_IN6:
case SIOCSGIFPREFIX_IN6:
case SIOCGIFPREFIX_IN6:
log(LOG_NOTICE,
"prefix ioctls are now invalidated. "
"please use ifconfig.\n");
return (EOPNOTSUPP);
}
switch (cmd) {
case SIOCSSCOPE6:
if (td != NULL) {
error = priv_check(td, PRIV_NETINET_SCOPE6);
if (error)
return (error);
}
/* FALLTHROUGH */
case SIOCGSCOPE6:
case SIOCGSCOPE6DEF:
return (scope6_ioctl(cmd, data, ifp));
}
/*
* Find address for this interface, if it exists.
*
* In netinet code, we have checked ifra_addr in SIOCSIF*ADDR operation
* only, and used the first interface address as the target of other
* operations (without checking ifra_addr). This was because netinet
* code/API assumed at most 1 interface address per interface.
* Since IPv6 allows a node to assign multiple addresses
* on a single interface, we almost always look and check the
* presence of ifra_addr, and reject invalid ones here.
* It also decreases duplicated code among SIOC*_IN6 operations.
*/
switch (cmd) {
case SIOCAIFADDR_IN6:
case SIOCSIFPHYADDR_IN6:
sa6 = &ifra->ifra_addr;
break;
case SIOCSIFADDR_IN6:
case SIOCGIFADDR_IN6:
case SIOCSIFDSTADDR_IN6:
case SIOCSIFNETMASK_IN6:
case SIOCGIFDSTADDR_IN6:
case SIOCGIFNETMASK_IN6:
case SIOCDIFADDR_IN6:
case SIOCGIFPSRCADDR_IN6:
case SIOCGIFPDSTADDR_IN6:
case SIOCGIFAFLAG_IN6:
case SIOCSNDFLUSH_IN6:
case SIOCSPFXFLUSH_IN6:
case SIOCSRTRFLUSH_IN6:
case SIOCGIFALIFETIME_IN6:
case SIOCGIFSTAT_IN6:
case SIOCGIFSTAT_ICMP6:
sa6 = &ifr->ifr_addr;
break;
case SIOCSIFADDR:
case SIOCSIFBRDADDR:
case SIOCSIFDSTADDR:
case SIOCSIFNETMASK:
/*
* Although we should pass any non-INET6 ioctl requests
* down to driver, we filter some legacy INET requests.
* Drivers trust SIOCSIFADDR et al to come from an already
* privileged layer, and do not perform any credentials
* checks or input validation.
*/
return (EINVAL);
default:
sa6 = NULL;
break;
}
if (sa6 && sa6->sin6_family == AF_INET6) {
if (sa6->sin6_scope_id != 0)
error = sa6_embedscope(sa6, 0);
else
error = in6_setscope(&sa6->sin6_addr, ifp, NULL);
if (error != 0)
return (error);
if (td != NULL && (error = prison_check_ip6(td->td_ucred,
&sa6->sin6_addr)) != 0)
return (error);
ia = in6ifa_ifpwithaddr(ifp, &sa6->sin6_addr);
} else
ia = NULL;
switch (cmd) {
case SIOCSIFADDR_IN6:
case SIOCSIFDSTADDR_IN6:
case SIOCSIFNETMASK_IN6:
/*
* Since IPv6 allows a node to assign multiple addresses
* on a single interface, SIOCSIFxxx ioctls are deprecated.
*/
/* we decided to obsolete this command (20000704) */
error = EINVAL;
goto out;
case SIOCDIFADDR_IN6:
/*
* for IPv4, we look for existing in_ifaddr here to allow
* "ifconfig if0 delete" to remove the first IPv4 address on
* the interface. For IPv6, as the spec allows multiple
* interface address from the day one, we consider "remove the
* first one" semantics to be not preferable.
*/
if (ia == NULL) {
error = EADDRNOTAVAIL;
goto out;
}
/* FALLTHROUGH */
case SIOCAIFADDR_IN6:
/*
* We always require users to specify a valid IPv6 address for
* the corresponding operation.
*/
if (ifra->ifra_addr.sin6_family != AF_INET6 ||
ifra->ifra_addr.sin6_len != sizeof(struct sockaddr_in6)) {
error = EAFNOSUPPORT;
goto out;
}
if (td != NULL) {
error = priv_check(td, (cmd == SIOCDIFADDR_IN6) ?
PRIV_NET_DELIFADDR : PRIV_NET_ADDIFADDR);
if (error)
goto out;
}
/* FALLTHROUGH */
case SIOCGIFSTAT_IN6:
case SIOCGIFSTAT_ICMP6:
if (ifp->if_afdata[AF_INET6] == NULL) {
error = EPFNOSUPPORT;
goto out;
}
break;
case SIOCGIFADDR_IN6:
/* This interface is basically deprecated. use SIOCGIFCONF. */
/* FALLTHROUGH */
case SIOCGIFAFLAG_IN6:
case SIOCGIFNETMASK_IN6:
case SIOCGIFDSTADDR_IN6:
case SIOCGIFALIFETIME_IN6:
/* must think again about its semantics */
if (ia == NULL) {
error = EADDRNOTAVAIL;
goto out;
}
break;
}
switch (cmd) {
case SIOCGIFADDR_IN6:
ifr->ifr_addr = ia->ia_addr;
if ((error = sa6_recoverscope(&ifr->ifr_addr)) != 0)
goto out;
break;
case SIOCGIFDSTADDR_IN6:
if ((ifp->if_flags & IFF_POINTOPOINT) == 0) {
error = EINVAL;
goto out;
}
ifr->ifr_dstaddr = ia->ia_dstaddr;
if ((error = sa6_recoverscope(&ifr->ifr_dstaddr)) != 0)
goto out;
break;
case SIOCGIFNETMASK_IN6:
ifr->ifr_addr = ia->ia_prefixmask;
break;
case SIOCGIFAFLAG_IN6:
ifr->ifr_ifru.ifru_flags6 = ia->ia6_flags;
break;
case SIOCGIFSTAT_IN6:
COUNTER_ARRAY_COPY(((struct in6_ifextra *)
ifp->if_afdata[AF_INET6])->in6_ifstat,
&ifr->ifr_ifru.ifru_stat,
sizeof(struct in6_ifstat) / sizeof(uint64_t));
break;
case SIOCGIFSTAT_ICMP6:
COUNTER_ARRAY_COPY(((struct in6_ifextra *)
ifp->if_afdata[AF_INET6])->icmp6_ifstat,
&ifr->ifr_ifru.ifru_icmp6stat,
sizeof(struct icmp6_ifstat) / sizeof(uint64_t));
break;
case SIOCGIFALIFETIME_IN6:
ifr->ifr_ifru.ifru_lifetime = ia->ia6_lifetime;
if (ia->ia6_lifetime.ia6t_vltime != ND6_INFINITE_LIFETIME) {
time_t maxexpire;
struct in6_addrlifetime *retlt =
&ifr->ifr_ifru.ifru_lifetime;
/*
* XXX: adjust expiration time assuming time_t is
* signed.
*/
maxexpire = (-1) &
~((time_t)1 << ((sizeof(maxexpire) * 8) - 1));
if (ia->ia6_lifetime.ia6t_vltime <
maxexpire - ia->ia6_updatetime) {
retlt->ia6t_expire = ia->ia6_updatetime +
ia->ia6_lifetime.ia6t_vltime;
} else
retlt->ia6t_expire = maxexpire;
}
if (ia->ia6_lifetime.ia6t_pltime != ND6_INFINITE_LIFETIME) {
time_t maxexpire;
struct in6_addrlifetime *retlt =
&ifr->ifr_ifru.ifru_lifetime;
/*
* XXX: adjust expiration time assuming time_t is
* signed.
*/
maxexpire = (-1) &
~((time_t)1 << ((sizeof(maxexpire) * 8) - 1));
if (ia->ia6_lifetime.ia6t_pltime <
maxexpire - ia->ia6_updatetime) {
retlt->ia6t_preferred = ia->ia6_updatetime +
ia->ia6_lifetime.ia6t_pltime;
} else
retlt->ia6t_preferred = maxexpire;
}
break;
case SIOCAIFADDR_IN6:
{
struct nd_prefixctl pr0;
struct nd_prefix *pr;
/*
* first, make or update the interface address structure,
* and link it to the list.
*/
if ((error = in6_update_ifa(ifp, ifra, ia, 0)) != 0)
goto out;
if (ia != NULL) {
if (ia->ia_ifa.ifa_carp)
(*carp_detach_p)(&ia->ia_ifa, true);
ifa_free(&ia->ia_ifa);
}
if ((ia = in6ifa_ifpwithaddr(ifp, &ifra->ifra_addr.sin6_addr))
== NULL) {
/*
* this can happen when the user specify the 0 valid
* lifetime.
*/
break;
}
if (cmd == ocmd && ifra->ifra_vhid > 0) {
if (carp_attach_p != NULL)
error = (*carp_attach_p)(&ia->ia_ifa,
ifra->ifra_vhid);
else
error = EPROTONOSUPPORT;
if (error)
goto out;
else
carp_attached = 1;
}
/*
* then, make the prefix on-link on the interface.
* XXX: we'd rather create the prefix before the address, but
* we need at least one address to install the corresponding
* interface route, so we configure the address first.
*/
/*
* convert mask to prefix length (prefixmask has already
* been validated in in6_update_ifa().
*/
bzero(&pr0, sizeof(pr0));
pr0.ndpr_ifp = ifp;
pr0.ndpr_plen = in6_mask2len(&ifra->ifra_prefixmask.sin6_addr,
NULL);
if (pr0.ndpr_plen == 128) {
/* we don't need to install a host route. */
goto aifaddr_out;
}
pr0.ndpr_prefix = ifra->ifra_addr;
/* apply the mask for safety. */
IN6_MASK_ADDR(&pr0.ndpr_prefix.sin6_addr,
&ifra->ifra_prefixmask.sin6_addr);
/*
* XXX: since we don't have an API to set prefix (not address)
* lifetimes, we just use the same lifetimes as addresses.
* The (temporarily) installed lifetimes can be overridden by
* later advertised RAs (when accept_rtadv is non 0), which is
* an intended behavior.
*/
pr0.ndpr_raf_onlink = 1; /* should be configurable? */
pr0.ndpr_raf_auto =
((ifra->ifra_flags & IN6_IFF_AUTOCONF) != 0);
pr0.ndpr_vltime = ifra->ifra_lifetime.ia6t_vltime;
pr0.ndpr_pltime = ifra->ifra_lifetime.ia6t_pltime;
/* add the prefix if not yet. */
if ((pr = nd6_prefix_lookup(&pr0)) == NULL) {
/*
* nd6_prelist_add will install the corresponding
* interface route.
*/
if ((error = nd6_prelist_add(&pr0, NULL, &pr)) != 0) {
if (carp_attached)
(*carp_detach_p)(&ia->ia_ifa, false);
goto out;
}
}
/* relate the address to the prefix */
if (ia->ia6_ndpr == NULL) {
ia->ia6_ndpr = pr;
pr->ndpr_addrcnt++;
/*
* If this is the first autoconf address from the
* prefix, create a temporary address as well
* (when required).
*/
if ((ia->ia6_flags & IN6_IFF_AUTOCONF) &&
V_ip6_use_tempaddr && pr->ndpr_addrcnt == 1) {
int e;
if ((e = in6_tmpifadd(ia, 1, 0)) != 0) {
log(LOG_NOTICE, "in6_control: failed "
"to create a temporary address, "
"errno=%d\n", e);
}
}
}
nd6_prefix_rele(pr);
/*
* this might affect the status of autoconfigured addresses,
* that is, this address might make other addresses detached.
*/
pfxlist_onlink_check();
aifaddr_out:
/*
* Try to clear the flag when a new IPv6 address is added
* onto an IFDISABLED interface and it succeeds.
*/
if (ND_IFINFO(ifp)->flags & ND6_IFF_IFDISABLED) {
struct in6_ndireq nd;
memset(&nd, 0, sizeof(nd));
nd.ndi.flags = ND_IFINFO(ifp)->flags;
nd.ndi.flags &= ~ND6_IFF_IFDISABLED;
if (nd6_ioctl(SIOCSIFINFO_FLAGS, (caddr_t)&nd, ifp) < 0)
log(LOG_NOTICE, "SIOCAIFADDR_IN6: "
"SIOCSIFINFO_FLAGS for -ifdisabled "
"failed.");
/*
* Ignore failure of clearing the flag intentionally.
* The failure means address duplication was detected.
*/
}
break;
}
case SIOCDIFADDR_IN6:
{
struct nd_prefix *pr;
/*
* If the address being deleted is the only one that owns
* the corresponding prefix, expire the prefix as well.
* XXX: theoretically, we don't have to worry about such
* relationship, since we separate the address management
* and the prefix management. We do this, however, to provide
* as much backward compatibility as possible in terms of
* the ioctl operation.
* Note that in6_purgeaddr() will decrement ndpr_addrcnt.
*/
pr = ia->ia6_ndpr;
in6_purgeaddr(&ia->ia_ifa);
if (pr != NULL && pr->ndpr_addrcnt == 0) {
ND6_WLOCK();
nd6_prefix_unlink(pr, NULL);
ND6_WUNLOCK();
nd6_prefix_del(pr);
}
EVENTHANDLER_INVOKE(ifaddr_event_ext, ifp, &ia->ia_ifa,
IFADDR_EVENT_DEL);
break;
}
default:
if (ifp->if_ioctl == NULL) {
error = EOPNOTSUPP;
goto out;
}
error = (*ifp->if_ioctl)(ifp, cmd, data);
goto out;
}
error = 0;
out:
if (ia != NULL)
ifa_free(&ia->ia_ifa);
return (error);
}
static struct in6_multi_mship *
in6_joingroup_legacy(struct ifnet *ifp, const struct in6_addr *mcaddr,
int *errorp, int delay)
{
struct in6_multi_mship *imm;
int error;
imm = malloc(sizeof(*imm), M_IP6MADDR, M_NOWAIT);
if (imm == NULL) {
*errorp = ENOBUFS;
return (NULL);
}
delay = (delay * PR_FASTHZ) / hz;
error = in6_joingroup(ifp, mcaddr, NULL, &imm->i6mm_maddr, delay);
if (error) {
*errorp = error;
free(imm, M_IP6MADDR);
return (NULL);
}
return (imm);
}
/*
* Join necessary multicast groups. Factored out from in6_update_ifa().
* This entire work should only be done once, for the default FIB.
*/
static int
in6_update_ifa_join_mc(struct ifnet *ifp, struct in6_aliasreq *ifra,
struct in6_ifaddr *ia, int flags, struct in6_multi **in6m_sol)
{
char ip6buf[INET6_ADDRSTRLEN];
struct in6_addr mltaddr;
struct in6_multi_mship *imm;
int delay, error;
KASSERT(in6m_sol != NULL, ("%s: in6m_sol is NULL", __func__));
/* Join solicited multicast addr for new host id. */
bzero(&mltaddr, sizeof(struct in6_addr));
mltaddr.s6_addr32[0] = IPV6_ADDR_INT32_MLL;
mltaddr.s6_addr32[2] = htonl(1);
mltaddr.s6_addr32[3] = ifra->ifra_addr.sin6_addr.s6_addr32[3];
mltaddr.s6_addr8[12] = 0xff;
if ((error = in6_setscope(&mltaddr, ifp, NULL)) != 0) {
/* XXX: should not happen */
log(LOG_ERR, "%s: in6_setscope failed\n", __func__);
goto cleanup;
}
delay = error = 0;
if ((flags & IN6_IFAUPDATE_DADDELAY)) {
/*
* We need a random delay for DAD on the address being
* configured. It also means delaying transmission of the
* corresponding MLD report to avoid report collision.
* [RFC 4861, Section 6.3.7]
*/
delay = arc4random() % (MAX_RTR_SOLICITATION_DELAY * hz);
}
imm = in6_joingroup_legacy(ifp, &mltaddr, &error, delay);
if (imm == NULL) {
nd6log((LOG_WARNING, "%s: in6_joingroup failed for %s on %s "
"(errno=%d)\n", __func__, ip6_sprintf(ip6buf, &mltaddr),
if_name(ifp), error));
goto cleanup;
}
LIST_INSERT_HEAD(&ia->ia6_memberships, imm, i6mm_chain);
*in6m_sol = imm->i6mm_maddr;
/*
* Join link-local all-nodes address.
*/
mltaddr = in6addr_linklocal_allnodes;
if ((error = in6_setscope(&mltaddr, ifp, NULL)) != 0)
goto cleanup; /* XXX: should not fail */
imm = in6_joingroup_legacy(ifp, &mltaddr, &error, 0);
if (imm == NULL) {
nd6log((LOG_WARNING, "%s: in6_joingroup failed for %s on %s "
"(errno=%d)\n", __func__, ip6_sprintf(ip6buf, &mltaddr),
if_name(ifp), error));
goto cleanup;
}
LIST_INSERT_HEAD(&ia->ia6_memberships, imm, i6mm_chain);
/*
* Join node information group address.
*/
delay = 0;
if ((flags & IN6_IFAUPDATE_DADDELAY)) {
/*
* The spec does not say anything about delay for this group,
* but the same logic should apply.
*/
delay = arc4random() % (MAX_RTR_SOLICITATION_DELAY * hz);
}
if (in6_nigroup(ifp, NULL, -1, &mltaddr) == 0) {
/* XXX jinmei */
imm = in6_joingroup_legacy(ifp, &mltaddr, &error, delay);
if (imm == NULL)
nd6log((LOG_WARNING,
"%s: in6_joingroup failed for %s on %s "
"(errno=%d)\n", __func__, ip6_sprintf(ip6buf,
&mltaddr), if_name(ifp), error));
/* XXX not very fatal, go on... */
else
LIST_INSERT_HEAD(&ia->ia6_memberships, imm, i6mm_chain);
}
if (V_icmp6_nodeinfo_oldmcprefix &&
in6_nigroup_oldmcprefix(ifp, NULL, -1, &mltaddr) == 0) {
imm = in6_joingroup_legacy(ifp, &mltaddr, &error, delay);
if (imm == NULL)
nd6log((LOG_WARNING,
"%s: in6_joingroup failed for %s on %s "
"(errno=%d)\n", __func__, ip6_sprintf(ip6buf,
&mltaddr), if_name(ifp), error));
/* XXX not very fatal, go on... */
else
LIST_INSERT_HEAD(&ia->ia6_memberships, imm, i6mm_chain);
}
/*
* Join interface-local all-nodes address.
* (ff01::1%ifN, and ff01::%ifN/32)
*/
mltaddr = in6addr_nodelocal_allnodes;
if ((error = in6_setscope(&mltaddr, ifp, NULL)) != 0)
goto cleanup; /* XXX: should not fail */
imm = in6_joingroup_legacy(ifp, &mltaddr, &error, 0);
if (imm == NULL) {
nd6log((LOG_WARNING, "%s: in6_joingroup failed for %s on %s "
"(errno=%d)\n", __func__, ip6_sprintf(ip6buf,
&mltaddr), if_name(ifp), error));
goto cleanup;
}
LIST_INSERT_HEAD(&ia->ia6_memberships, imm, i6mm_chain);
cleanup:
return (error);
}
/*
* Update parameters of an IPv6 interface address.
* If necessary, a new entry is created and linked into address chains.
* This function is separated from in6_control().
*/
int
in6_update_ifa(struct ifnet *ifp, struct in6_aliasreq *ifra,
struct in6_ifaddr *ia, int flags)
{
int error, hostIsNew = 0;
if ((error = in6_validate_ifra(ifp, ifra, ia, flags)) != 0)
return (error);
if (ia == NULL) {
hostIsNew = 1;
if ((ia = in6_alloc_ifa(ifp, ifra, flags)) == NULL)
return (ENOBUFS);
}
error = in6_update_ifa_internal(ifp, ifra, ia, hostIsNew, flags);
if (error != 0) {
if (hostIsNew != 0) {
in6_unlink_ifa(ia, ifp);
ifa_free(&ia->ia_ifa);
}
return (error);
}
if (hostIsNew)
error = in6_broadcast_ifa(ifp, ifra, ia, flags);
return (error);
}
/*
* Fill in basic IPv6 address request info.
*/
void
in6_prepare_ifra(struct in6_aliasreq *ifra, const struct in6_addr *addr,
const struct in6_addr *mask)
{
memset(ifra, 0, sizeof(struct in6_aliasreq));
ifra->ifra_addr.sin6_family = AF_INET6;
ifra->ifra_addr.sin6_len = sizeof(struct sockaddr_in6);
if (addr != NULL)
ifra->ifra_addr.sin6_addr = *addr;
ifra->ifra_prefixmask.sin6_family = AF_INET6;
ifra->ifra_prefixmask.sin6_len = sizeof(struct sockaddr_in6);
if (mask != NULL)
ifra->ifra_prefixmask.sin6_addr = *mask;
}
static int
in6_validate_ifra(struct ifnet *ifp, struct in6_aliasreq *ifra,
struct in6_ifaddr *ia, int flags)
{
int plen = -1;
struct sockaddr_in6 dst6;
struct in6_addrlifetime *lt;
char ip6buf[INET6_ADDRSTRLEN];
/* Validate parameters */
if (ifp == NULL || ifra == NULL) /* this maybe redundant */
return (EINVAL);
/*
* The destination address for a p2p link must have a family
* of AF_UNSPEC or AF_INET6.
*/
if ((ifp->if_flags & IFF_POINTOPOINT) != 0 &&
ifra->ifra_dstaddr.sin6_family != AF_INET6 &&
ifra->ifra_dstaddr.sin6_family != AF_UNSPEC)
return (EAFNOSUPPORT);
/*
* Validate address
*/
if (ifra->ifra_addr.sin6_len != sizeof(struct sockaddr_in6) ||
ifra->ifra_addr.sin6_family != AF_INET6)
return (EINVAL);
/*
* validate ifra_prefixmask. don't check sin6_family, netmask
* does not carry fields other than sin6_len.
*/
if (ifra->ifra_prefixmask.sin6_len > sizeof(struct sockaddr_in6))
return (EINVAL);
/*
* Because the IPv6 address architecture is classless, we require
* users to specify a (non 0) prefix length (mask) for a new address.
* We also require the prefix (when specified) mask is valid, and thus
* reject a non-consecutive mask.
*/
if (ia == NULL && ifra->ifra_prefixmask.sin6_len == 0)
return (EINVAL);
if (ifra->ifra_prefixmask.sin6_len != 0) {
plen = in6_mask2len(&ifra->ifra_prefixmask.sin6_addr,
(u_char *)&ifra->ifra_prefixmask +
ifra->ifra_prefixmask.sin6_len);
if (plen <= 0)
return (EINVAL);
} else {
/*
* In this case, ia must not be NULL. We just use its prefix
* length.
*/
plen = in6_mask2len(&ia->ia_prefixmask.sin6_addr, NULL);
}
/*
* If the destination address on a p2p interface is specified,
* and the address is a scoped one, validate/set the scope
* zone identifier.
*/
dst6 = ifra->ifra_dstaddr;
if ((ifp->if_flags & (IFF_POINTOPOINT|IFF_LOOPBACK)) != 0 &&
(dst6.sin6_family == AF_INET6)) {
struct in6_addr in6_tmp;
u_int32_t zoneid;
in6_tmp = dst6.sin6_addr;
if (in6_setscope(&in6_tmp, ifp, &zoneid))
return (EINVAL); /* XXX: should be impossible */
if (dst6.sin6_scope_id != 0) {
if (dst6.sin6_scope_id != zoneid)
return (EINVAL);
} else /* user omit to specify the ID. */
dst6.sin6_scope_id = zoneid;
/* convert into the internal form */
if (sa6_embedscope(&dst6, 0))
return (EINVAL); /* XXX: should be impossible */
}
/* Modify original ifra_dstaddr to reflect changes */
ifra->ifra_dstaddr = dst6;
/*
* The destination address can be specified only for a p2p or a
* loopback interface. If specified, the corresponding prefix length
* must be 128.
*/
if (ifra->ifra_dstaddr.sin6_family == AF_INET6) {
if ((ifp->if_flags & (IFF_POINTOPOINT|IFF_LOOPBACK)) == 0) {
/* XXX: noisy message */
nd6log((LOG_INFO, "in6_update_ifa: a destination can "
"be specified for a p2p or a loopback IF only\n"));
return (EINVAL);
}
if (plen != 128) {
nd6log((LOG_INFO, "in6_update_ifa: prefixlen should "
"be 128 when dstaddr is specified\n"));
return (EINVAL);
}
}
/* lifetime consistency check */
lt = &ifra->ifra_lifetime;
if (lt->ia6t_pltime > lt->ia6t_vltime)
return (EINVAL);
if (lt->ia6t_vltime == 0) {
/*
* the following log might be noisy, but this is a typical
* configuration mistake or a tool's bug.
*/
nd6log((LOG_INFO,
"in6_update_ifa: valid lifetime is 0 for %s\n",
ip6_sprintf(ip6buf, &ifra->ifra_addr.sin6_addr)));
if (ia == NULL)
return (0); /* there's nothing to do */
}
/* Check prefix mask */
if (ia != NULL && ifra->ifra_prefixmask.sin6_len != 0) {
/*
* We prohibit changing the prefix length of an existing
* address, because
* + such an operation should be rare in IPv6, and
* + the operation would confuse prefix management.
*/
if (ia->ia_prefixmask.sin6_len != 0 &&
in6_mask2len(&ia->ia_prefixmask.sin6_addr, NULL) != plen) {
nd6log((LOG_INFO, "in6_validate_ifa: the prefix length "
"of an existing %s address should not be changed\n",
ip6_sprintf(ip6buf, &ia->ia_addr.sin6_addr)));
return (EINVAL);
}
}
return (0);
}
/*
* Allocate a new ifaddr and link it into chains.
*/
static struct in6_ifaddr *
in6_alloc_ifa(struct ifnet *ifp, struct in6_aliasreq *ifra, int flags)
{
struct in6_ifaddr *ia;
/*
* When in6_alloc_ifa() is called in a process of a received
* RA, it is called under an interrupt context. So, we should
* call malloc with M_NOWAIT.
*/
ia = (struct in6_ifaddr *)ifa_alloc(sizeof(*ia), M_NOWAIT);
if (ia == NULL)
return (NULL);
LIST_INIT(&ia->ia6_memberships);
/* Initialize the address and masks, and put time stamp */
ia->ia_ifa.ifa_addr = (struct sockaddr *)&ia->ia_addr;
ia->ia_addr.sin6_family = AF_INET6;
ia->ia_addr.sin6_len = sizeof(ia->ia_addr);
/* XXX: Can we assign ,sin6_addr and skip the rest? */
ia->ia_addr = ifra->ifra_addr;
ia->ia6_createtime = time_uptime;
if ((ifp->if_flags & (IFF_POINTOPOINT | IFF_LOOPBACK)) != 0) {
/*
* Some functions expect that ifa_dstaddr is not
* NULL for p2p interfaces.
*/
ia->ia_ifa.ifa_dstaddr =
(struct sockaddr *)&ia->ia_dstaddr;
} else {
ia->ia_ifa.ifa_dstaddr = NULL;
}
/* set prefix mask if any */
ia->ia_ifa.ifa_netmask = (struct sockaddr *)&ia->ia_prefixmask;
if (ifra->ifra_prefixmask.sin6_len != 0) {
ia->ia_prefixmask.sin6_family = AF_INET6;
ia->ia_prefixmask.sin6_len = ifra->ifra_prefixmask.sin6_len;
ia->ia_prefixmask.sin6_addr = ifra->ifra_prefixmask.sin6_addr;
}
ia->ia_ifp = ifp;
ifa_ref(&ia->ia_ifa); /* if_addrhead */
IF_ADDR_WLOCK(ifp);
CK_STAILQ_INSERT_TAIL(&ifp->if_addrhead, &ia->ia_ifa, ifa_link);
IF_ADDR_WUNLOCK(ifp);
ifa_ref(&ia->ia_ifa); /* in6_ifaddrhead */
IN6_IFADDR_WLOCK();
CK_STAILQ_INSERT_TAIL(&V_in6_ifaddrhead, ia, ia_link);
CK_LIST_INSERT_HEAD(IN6ADDR_HASH(&ia->ia_addr.sin6_addr), ia, ia6_hash);
IN6_IFADDR_WUNLOCK();
return (ia);
}
/*
* Update/configure interface address parameters:
*
* 1) Update lifetime
* 2) Update interface metric ad flags
* 3) Notify other subsystems
*/
static int
in6_update_ifa_internal(struct ifnet *ifp, struct in6_aliasreq *ifra,
struct in6_ifaddr *ia, int hostIsNew, int flags)
{
int error;
/* update timestamp */
ia->ia6_updatetime = time_uptime;
/*
* Set lifetimes. We do not refer to ia6t_expire and ia6t_preferred
* to see if the address is deprecated or invalidated, but initialize
* these members for applications.
*/
ia->ia6_lifetime = ifra->ifra_lifetime;
if (ia->ia6_lifetime.ia6t_vltime != ND6_INFINITE_LIFETIME) {
ia->ia6_lifetime.ia6t_expire =
time_uptime + ia->ia6_lifetime.ia6t_vltime;
} else
ia->ia6_lifetime.ia6t_expire = 0;
if (ia->ia6_lifetime.ia6t_pltime != ND6_INFINITE_LIFETIME) {
ia->ia6_lifetime.ia6t_preferred =
time_uptime + ia->ia6_lifetime.ia6t_pltime;
} else
ia->ia6_lifetime.ia6t_preferred = 0;
/*
* backward compatibility - if IN6_IFF_DEPRECATED is set from the
* userland, make it deprecated.
*/
if ((ifra->ifra_flags & IN6_IFF_DEPRECATED) != 0) {
ia->ia6_lifetime.ia6t_pltime = 0;
ia->ia6_lifetime.ia6t_preferred = time_uptime;
}
/*
* configure address flags.
*/
ia->ia6_flags = ifra->ifra_flags;
/*
* Make the address tentative before joining multicast addresses,
* so that corresponding MLD responses would not have a tentative
* source address.
*/
ia->ia6_flags &= ~IN6_IFF_DUPLICATED; /* safety */
/*
* DAD should be performed for an new address or addresses on
* an interface with ND6_IFF_IFDISABLED.
*/
if (in6if_do_dad(ifp) &&
(hostIsNew || (ND_IFINFO(ifp)->flags & ND6_IFF_IFDISABLED)))
ia->ia6_flags |= IN6_IFF_TENTATIVE;
/* notify other subsystems */
error = in6_notify_ifa(ifp, ia, ifra, hostIsNew);
return (error);
}
/*
* Do link-level ifa job:
* 1) Add lle entry for added address
* 2) Notifies routing socket users about new address
* 3) join appropriate multicast group
* 4) start DAD if enabled
*/
static int
in6_broadcast_ifa(struct ifnet *ifp, struct in6_aliasreq *ifra,
struct in6_ifaddr *ia, int flags)
{
struct in6_multi *in6m_sol;
int error = 0;
/* Add local address to lltable, if necessary (ex. on p2p link). */
if ((error = nd6_add_ifa_lle(ia)) != 0) {
in6_purgeaddr(&ia->ia_ifa);
ifa_free(&ia->ia_ifa);
return (error);
}
/* Join necessary multicast groups. */
in6m_sol = NULL;
if ((ifp->if_flags & IFF_MULTICAST) != 0) {
error = in6_update_ifa_join_mc(ifp, ifra, ia, flags, &in6m_sol);
if (error != 0) {
in6_purgeaddr(&ia->ia_ifa);
ifa_free(&ia->ia_ifa);
return (error);
}
}
/* Perform DAD, if the address is TENTATIVE. */
if ((ia->ia6_flags & IN6_IFF_TENTATIVE)) {
int delay, mindelay, maxdelay;
delay = 0;
if ((flags & IN6_IFAUPDATE_DADDELAY)) {
/*
* We need to impose a delay before sending an NS
* for DAD. Check if we also needed a delay for the
* corresponding MLD message. If we did, the delay
* should be larger than the MLD delay (this could be
* relaxed a bit, but this simple logic is at least
* safe).
* XXX: Break data hiding guidelines and look at
* state for the solicited multicast group.
*/
mindelay = 0;
if (in6m_sol != NULL &&
in6m_sol->in6m_state == MLD_REPORTING_MEMBER) {
mindelay = in6m_sol->in6m_timer;
}
maxdelay = MAX_RTR_SOLICITATION_DELAY * hz;
if (maxdelay - mindelay == 0)
delay = 0;
else {
delay =
(arc4random() % (maxdelay - mindelay)) +
mindelay;
}
}
nd6_dad_start((struct ifaddr *)ia, delay);
}
in6_newaddrmsg(ia, RTM_ADD);
ifa_free(&ia->ia_ifa);
return (error);
}
+/*
+ * Adds or deletes interface route for p2p ifa.
+ * Returns 0 on success or errno.
+ */
+static int
+in6_handle_dstaddr_rtrequest(int cmd, struct in6_ifaddr *ia)
+{
+ struct epoch_tracker et;
+ struct ifaddr *ifa = &ia->ia_ifa;
+ int error;
+
+ /* Prepare gateway */
+ struct sockaddr_dl_short sdl = {
+ .sdl_family = AF_LINK,
+ .sdl_len = sizeof(struct sockaddr_dl_short),
+ .sdl_type = ifa->ifa_ifp->if_type,
+ .sdl_index = ifa->ifa_ifp->if_index,
+ };
+
+ struct sockaddr_in6 dst = {
+ .sin6_family = AF_INET6,
+ .sin6_len = sizeof(struct sockaddr_in6),
+ .sin6_addr = ia->ia_dstaddr.sin6_addr,
+ };
+
+ struct rt_addrinfo info = {
+ .rti_ifa = ifa,
+ .rti_flags = RTF_PINNED | RTF_HOST,
+ .rti_info = {
+ [RTAX_DST] = (struct sockaddr *)&dst,
+ [RTAX_GATEWAY] = (struct sockaddr *)&sdl,
+ },
+ };
+ /* Don't set additional per-gw filters on removal */
+
+ NET_EPOCH_ENTER(et);
+ error = rib_handle_ifaddr_info(ifa->ifa_ifp->if_fib, cmd, &info);
+ NET_EPOCH_EXIT(et);
+
+ return (error);
+}
+
void
in6_purgeaddr(struct ifaddr *ifa)
{
struct ifnet *ifp = ifa->ifa_ifp;
struct in6_ifaddr *ia = (struct in6_ifaddr *) ifa;
struct in6_multi_mship *imm;
int plen, error;
if (ifa->ifa_carp)
(*carp_detach_p)(ifa, false);
/*
* Remove the loopback route to the interface address.
* The check for the current setting of "nd6_useloopback"
* is not needed.
*/
if (ia->ia_flags & IFA_RTSELF) {
error = ifa_del_loopback_route((struct ifaddr *)ia,
(struct sockaddr *)&ia->ia_addr);
if (error == 0)
ia->ia_flags &= ~IFA_RTSELF;
}
/* stop DAD processing */
nd6_dad_stop(ifa);
/* Leave multicast groups. */
while ((imm = LIST_FIRST(&ia->ia6_memberships)) != NULL) {
LIST_REMOVE(imm, i6mm_chain);
if (imm->i6mm_maddr != NULL)
in6_leavegroup(imm->i6mm_maddr, NULL);
free(imm, M_IP6MADDR);
}
+ /* Check if we need to remove p2p route */
plen = in6_mask2len(&ia->ia_prefixmask.sin6_addr, NULL); /* XXX */
+ if (ia->ia_dstaddr.sin6_family != AF_INET6)
+ plen = 0;
if ((ia->ia_flags & IFA_ROUTE) && plen == 128) {
- error = rtinit(&(ia->ia_ifa), RTM_DELETE, ia->ia_flags |
- (ia->ia_dstaddr.sin6_family == AF_INET6 ? RTF_HOST : 0));
+ error = in6_handle_dstaddr_rtrequest(RTM_DELETE, ia);
if (error != 0)
log(LOG_INFO, "%s: err=%d, destination address delete "
"failed\n", __func__, error);
ia->ia_flags &= ~IFA_ROUTE;
}
in6_newaddrmsg(ia, RTM_DELETE);
in6_unlink_ifa(ia, ifp);
}
static void
in6_unlink_ifa(struct in6_ifaddr *ia, struct ifnet *ifp)
{
char ip6buf[INET6_ADDRSTRLEN];
int remove_lle;
IF_ADDR_WLOCK(ifp);
CK_STAILQ_REMOVE(&ifp->if_addrhead, &ia->ia_ifa, ifaddr, ifa_link);
IF_ADDR_WUNLOCK(ifp);
ifa_free(&ia->ia_ifa); /* if_addrhead */
/*
* Defer the release of what might be the last reference to the
* in6_ifaddr so that it can't be freed before the remainder of the
* cleanup.
*/
IN6_IFADDR_WLOCK();
CK_STAILQ_REMOVE(&V_in6_ifaddrhead, ia, in6_ifaddr, ia_link);
CK_LIST_REMOVE(ia, ia6_hash);
IN6_IFADDR_WUNLOCK();
/*
* Release the reference to the base prefix. There should be a
* positive reference.
*/
remove_lle = 0;
if (ia->ia6_ndpr == NULL) {
nd6log((LOG_NOTICE,
"in6_unlink_ifa: autoconf'ed address "
"%s has no prefix\n", ip6_sprintf(ip6buf, IA6_IN6(ia))));
} else {
ia->ia6_ndpr->ndpr_addrcnt--;
/* Do not delete lles within prefix if refcont != 0 */
if (ia->ia6_ndpr->ndpr_addrcnt == 0)
remove_lle = 1;
ia->ia6_ndpr = NULL;
}
nd6_rem_ifa_lle(ia, remove_lle);
/*
* Also, if the address being removed is autoconf'ed, call
* pfxlist_onlink_check() since the release might affect the status of
* other (detached) addresses.
*/
if ((ia->ia6_flags & IN6_IFF_AUTOCONF)) {
pfxlist_onlink_check();
}
ifa_free(&ia->ia_ifa); /* in6_ifaddrhead */
}
/*
* Notifies other subsystems about address change/arrival:
* 1) Notifies device handler on the first IPv6 address assignment
* 2) Handle routing table changes for P2P links and route
* 3) Handle routing table changes for address host route
*/
static int
in6_notify_ifa(struct ifnet *ifp, struct in6_ifaddr *ia,
struct in6_aliasreq *ifra, int hostIsNew)
{
int error = 0, plen, ifacount = 0;
struct ifaddr *ifa;
struct sockaddr_in6 *pdst;
char ip6buf[INET6_ADDRSTRLEN];
/*
* Give the interface a chance to initialize
* if this is its first address,
*/
if (hostIsNew != 0) {
struct epoch_tracker et;
NET_EPOCH_ENTER(et);
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family != AF_INET6)
continue;
ifacount++;
}
NET_EPOCH_EXIT(et);
}
if (ifacount <= 1 && ifp->if_ioctl) {
error = (*ifp->if_ioctl)(ifp, SIOCSIFADDR, (caddr_t)ia);
if (error)
goto done;
}
/*
* If a new destination address is specified, scrub the old one and
* install the new destination. Note that the interface must be
* p2p or loopback.
*/
pdst = &ifra->ifra_dstaddr;
if (pdst->sin6_family == AF_INET6 &&
!IN6_ARE_ADDR_EQUAL(&pdst->sin6_addr, &ia->ia_dstaddr.sin6_addr)) {
if ((ia->ia_flags & IFA_ROUTE) != 0 &&
- (rtinit(&(ia->ia_ifa), (int)RTM_DELETE, RTF_HOST) != 0)) {
+ (in6_handle_dstaddr_rtrequest(RTM_DELETE, ia) != 0)) {
nd6log((LOG_ERR, "in6_update_ifa_internal: failed to "
"remove a route to the old destination: %s\n",
ip6_sprintf(ip6buf, &ia->ia_addr.sin6_addr)));
/* proceed anyway... */
} else
ia->ia_flags &= ~IFA_ROUTE;
ia->ia_dstaddr = *pdst;
}
/*
* If a new destination address is specified for a point-to-point
* interface, install a route to the destination as an interface
* direct route.
* XXX: the logic below rejects assigning multiple addresses on a p2p
* interface that share the same destination.
*/
plen = in6_mask2len(&ia->ia_prefixmask.sin6_addr, NULL); /* XXX */
if (!(ia->ia_flags & IFA_ROUTE) && plen == 128 &&
ia->ia_dstaddr.sin6_family == AF_INET6) {
- int rtflags = RTF_UP | RTF_HOST;
/*
* Handle the case for ::1 .
*/
if (ifp->if_flags & IFF_LOOPBACK)
ia->ia_flags |= IFA_RTSELF;
- error = rtinit(&ia->ia_ifa, RTM_ADD, ia->ia_flags | rtflags);
+ error = in6_handle_dstaddr_rtrequest(RTM_ADD, ia);
if (error)
goto done;
ia->ia_flags |= IFA_ROUTE;
}
/*
* add a loopback route to self if not exists
*/
if (!(ia->ia_flags & IFA_RTSELF) && V_nd6_useloopback) {
error = ifa_add_loopback_route((struct ifaddr *)ia,
(struct sockaddr *)&ia->ia_addr);
if (error == 0)
ia->ia_flags |= IFA_RTSELF;
}
done:
WITNESS_WARN(WARN_GIANTOK | WARN_SLEEPOK, NULL,
"Invoking IPv6 network device address event may sleep");
ifa_ref(&ia->ia_ifa);
EVENTHANDLER_INVOKE(ifaddr_event_ext, ifp, &ia->ia_ifa,
IFADDR_EVENT_ADD);
ifa_free(&ia->ia_ifa);
return (error);
}
/*
* Find an IPv6 interface link-local address specific to an interface.
* ifaddr is returned referenced.
*/
struct in6_ifaddr *
in6ifa_ifpforlinklocal(struct ifnet *ifp, int ignoreflags)
{
struct ifaddr *ifa;
NET_EPOCH_ASSERT();
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family != AF_INET6)
continue;
if (IN6_IS_ADDR_LINKLOCAL(IFA_IN6(ifa))) {
if ((((struct in6_ifaddr *)ifa)->ia6_flags &
ignoreflags) != 0)
continue;
ifa_ref(ifa);
break;
}
}
return ((struct in6_ifaddr *)ifa);
}
/*
* find the interface address corresponding to a given IPv6 address.
* ifaddr is returned referenced.
*/
struct in6_ifaddr *
in6ifa_ifwithaddr(const struct in6_addr *addr, uint32_t zoneid)
{
struct rm_priotracker in6_ifa_tracker;
struct in6_ifaddr *ia;
IN6_IFADDR_RLOCK(&in6_ifa_tracker);
CK_LIST_FOREACH(ia, IN6ADDR_HASH(addr), ia6_hash) {
if (IN6_ARE_ADDR_EQUAL(IA6_IN6(ia), addr)) {
if (zoneid != 0 &&
zoneid != ia->ia_addr.sin6_scope_id)
continue;
ifa_ref(&ia->ia_ifa);
break;
}
}
IN6_IFADDR_RUNLOCK(&in6_ifa_tracker);
return (ia);
}
/*
* find the internet address corresponding to a given interface and address.
* ifaddr is returned referenced.
*/
struct in6_ifaddr *
in6ifa_ifpwithaddr(struct ifnet *ifp, const struct in6_addr *addr)
{
struct epoch_tracker et;
struct ifaddr *ifa;
NET_EPOCH_ENTER(et);
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family != AF_INET6)
continue;
if (IN6_ARE_ADDR_EQUAL(addr, IFA_IN6(ifa))) {
ifa_ref(ifa);
break;
}
}
NET_EPOCH_EXIT(et);
return ((struct in6_ifaddr *)ifa);
}
/*
* Find a link-local scoped address on ifp and return it if any.
*/
struct in6_ifaddr *
in6ifa_llaonifp(struct ifnet *ifp)
{
struct epoch_tracker et;
struct sockaddr_in6 *sin6;
struct ifaddr *ifa;
if (ND_IFINFO(ifp)->flags & ND6_IFF_IFDISABLED)
return (NULL);
NET_EPOCH_ENTER(et);
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family != AF_INET6)
continue;
sin6 = (struct sockaddr_in6 *)ifa->ifa_addr;
if (IN6_IS_SCOPE_LINKLOCAL(&sin6->sin6_addr) ||
IN6_IS_ADDR_MC_INTFACELOCAL(&sin6->sin6_addr) ||
IN6_IS_ADDR_MC_NODELOCAL(&sin6->sin6_addr))
break;
}
NET_EPOCH_EXIT(et);
return ((struct in6_ifaddr *)ifa);
}
/*
* Convert IP6 address to printable (loggable) representation. Caller
* has to make sure that ip6buf is at least INET6_ADDRSTRLEN long.
*/
static char digits[] = "0123456789abcdef";
char *
ip6_sprintf(char *ip6buf, const struct in6_addr *addr)
{
int i, cnt = 0, maxcnt = 0, idx = 0, index = 0;
char *cp;
const u_int16_t *a = (const u_int16_t *)addr;
const u_int8_t *d;
int dcolon = 0, zero = 0;
cp = ip6buf;
for (i = 0; i < 8; i++) {
if (*(a + i) == 0) {
cnt++;
if (cnt == 1)
idx = i;
}
else if (maxcnt < cnt) {
maxcnt = cnt;
index = idx;
cnt = 0;
}
}
if (maxcnt < cnt) {
maxcnt = cnt;
index = idx;
}
for (i = 0; i < 8; i++) {
if (dcolon == 1) {
if (*a == 0) {
if (i == 7)
*cp++ = ':';
a++;
continue;
} else
dcolon = 2;
}
if (*a == 0) {
if (dcolon == 0 && *(a + 1) == 0 && i == index) {
if (i == 0)
*cp++ = ':';
*cp++ = ':';
dcolon = 1;
} else {
*cp++ = '0';
*cp++ = ':';
}
a++;
continue;
}
d = (const u_char *)a;
/* Try to eliminate leading zeros in printout like in :0001. */
zero = 1;
*cp = digits[*d >> 4];
if (*cp != '0') {
zero = 0;
cp++;
}
*cp = digits[*d++ & 0xf];
if (zero == 0 || (*cp != '0')) {
zero = 0;
cp++;
}
*cp = digits[*d >> 4];
if (zero == 0 || (*cp != '0')) {
zero = 0;
cp++;
}
*cp++ = digits[*d & 0xf];
*cp++ = ':';
a++;
}
*--cp = '\0';
return (ip6buf);
}
int
in6_localaddr(struct in6_addr *in6)
{
struct rm_priotracker in6_ifa_tracker;
struct in6_ifaddr *ia;
if (IN6_IS_ADDR_LOOPBACK(in6) || IN6_IS_ADDR_LINKLOCAL(in6))
return 1;
IN6_IFADDR_RLOCK(&in6_ifa_tracker);
CK_STAILQ_FOREACH(ia, &V_in6_ifaddrhead, ia_link) {
if (IN6_ARE_MASKED_ADDR_EQUAL(in6, &ia->ia_addr.sin6_addr,
&ia->ia_prefixmask.sin6_addr)) {
IN6_IFADDR_RUNLOCK(&in6_ifa_tracker);
return 1;
}
}
IN6_IFADDR_RUNLOCK(&in6_ifa_tracker);
return (0);
}
/*
* Return 1 if an internet address is for the local host and configured
* on one of its interfaces.
*/
int
in6_localip(struct in6_addr *in6)
{
struct rm_priotracker in6_ifa_tracker;
struct in6_ifaddr *ia;
IN6_IFADDR_RLOCK(&in6_ifa_tracker);
CK_LIST_FOREACH(ia, IN6ADDR_HASH(in6), ia6_hash) {
if (IN6_ARE_ADDR_EQUAL(in6, &ia->ia_addr.sin6_addr)) {
IN6_IFADDR_RUNLOCK(&in6_ifa_tracker);
return (1);
}
}
IN6_IFADDR_RUNLOCK(&in6_ifa_tracker);
return (0);
}
/*
* Return 1 if an internet address is configured on an interface.
*/
int
in6_ifhasaddr(struct ifnet *ifp, struct in6_addr *addr)
{
struct in6_addr in6;
struct ifaddr *ifa;
struct in6_ifaddr *ia6;
NET_EPOCH_ASSERT();
in6 = *addr;
if (in6_clearscope(&in6))
return (0);
in6_setscope(&in6, ifp, NULL);
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family != AF_INET6)
continue;
ia6 = (struct in6_ifaddr *)ifa;
if (IN6_ARE_ADDR_EQUAL(&ia6->ia_addr.sin6_addr, &in6))
return (1);
}
return (0);
}
int
in6_is_addr_deprecated(struct sockaddr_in6 *sa6)
{
struct rm_priotracker in6_ifa_tracker;
struct in6_ifaddr *ia;
IN6_IFADDR_RLOCK(&in6_ifa_tracker);
CK_LIST_FOREACH(ia, IN6ADDR_HASH(&sa6->sin6_addr), ia6_hash) {
if (IN6_ARE_ADDR_EQUAL(IA6_IN6(ia), &sa6->sin6_addr)) {
if (ia->ia6_flags & IN6_IFF_DEPRECATED) {
IN6_IFADDR_RUNLOCK(&in6_ifa_tracker);
return (1); /* true */
}
break;
}
}
IN6_IFADDR_RUNLOCK(&in6_ifa_tracker);
return (0); /* false */
}
/*
* return length of part which dst and src are equal
* hard coding...
*/
int
in6_matchlen(struct in6_addr *src, struct in6_addr *dst)
{
int match = 0;
u_char *s = (u_char *)src, *d = (u_char *)dst;
u_char *lim = s + 16, r;
while (s < lim)
if ((r = (*d++ ^ *s++)) != 0) {
while (r < 128) {
match++;
r <<= 1;
}
break;
} else
match += 8;
return match;
}
/* XXX: to be scope conscious */
int
in6_are_prefix_equal(struct in6_addr *p1, struct in6_addr *p2, int len)
{
int bytelen, bitlen;
/* sanity check */
if (0 > len || len > 128) {
log(LOG_ERR, "in6_are_prefix_equal: invalid prefix length(%d)\n",
len);
return (0);
}
bytelen = len / 8;
bitlen = len % 8;
if (bcmp(&p1->s6_addr, &p2->s6_addr, bytelen))
return (0);
if (bitlen != 0 &&
p1->s6_addr[bytelen] >> (8 - bitlen) !=
p2->s6_addr[bytelen] >> (8 - bitlen))
return (0);
return (1);
}
void
in6_prefixlen2mask(struct in6_addr *maskp, int len)
{
u_char maskarray[8] = {0x80, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc, 0xfe, 0xff};
int bytelen, bitlen, i;
/* sanity check */
if (0 > len || len > 128) {
log(LOG_ERR, "in6_prefixlen2mask: invalid prefix length(%d)\n",
len);
return;
}
bzero(maskp, sizeof(*maskp));
bytelen = len / 8;
bitlen = len % 8;
for (i = 0; i < bytelen; i++)
maskp->s6_addr[i] = 0xff;
if (bitlen)
maskp->s6_addr[bytelen] = maskarray[bitlen - 1];
}
/*
* return the best address out of the same scope. if no address was
* found, return the first valid address from designated IF.
*/
struct in6_ifaddr *
in6_ifawithifp(struct ifnet *ifp, struct in6_addr *dst)
{
int dst_scope = in6_addrscope(dst), blen = -1, tlen;
struct ifaddr *ifa;
struct in6_ifaddr *besta = NULL;
struct in6_ifaddr *dep[2]; /* last-resort: deprecated */
NET_EPOCH_ASSERT();
dep[0] = dep[1] = NULL;
/*
* We first look for addresses in the same scope.
* If there is one, return it.
* If two or more, return one which matches the dst longest.
* If none, return one of global addresses assigned other ifs.
*/
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family != AF_INET6)
continue;
if (((struct in6_ifaddr *)ifa)->ia6_flags & IN6_IFF_ANYCAST)
continue; /* XXX: is there any case to allow anycast? */
if (((struct in6_ifaddr *)ifa)->ia6_flags & IN6_IFF_NOTREADY)
continue; /* don't use this interface */
if (((struct in6_ifaddr *)ifa)->ia6_flags & IN6_IFF_DETACHED)
continue;
if (((struct in6_ifaddr *)ifa)->ia6_flags & IN6_IFF_DEPRECATED) {
if (V_ip6_use_deprecated)
dep[0] = (struct in6_ifaddr *)ifa;
continue;
}
if (dst_scope == in6_addrscope(IFA_IN6(ifa))) {
/*
* call in6_matchlen() as few as possible
*/
if (besta) {
if (blen == -1)
blen = in6_matchlen(&besta->ia_addr.sin6_addr, dst);
tlen = in6_matchlen(IFA_IN6(ifa), dst);
if (tlen > blen) {
blen = tlen;
besta = (struct in6_ifaddr *)ifa;
}
} else
besta = (struct in6_ifaddr *)ifa;
}
}
if (besta) {
ifa_ref(&besta->ia_ifa);
return (besta);
}
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family != AF_INET6)
continue;
if (((struct in6_ifaddr *)ifa)->ia6_flags & IN6_IFF_ANYCAST)
continue; /* XXX: is there any case to allow anycast? */
if (((struct in6_ifaddr *)ifa)->ia6_flags & IN6_IFF_NOTREADY)
continue; /* don't use this interface */
if (((struct in6_ifaddr *)ifa)->ia6_flags & IN6_IFF_DETACHED)
continue;
if (((struct in6_ifaddr *)ifa)->ia6_flags & IN6_IFF_DEPRECATED) {
if (V_ip6_use_deprecated)
dep[1] = (struct in6_ifaddr *)ifa;
continue;
}
if (ifa != NULL)
ifa_ref(ifa);
return (struct in6_ifaddr *)ifa;
}
/* use the last-resort values, that are, deprecated addresses */
if (dep[0]) {
ifa_ref((struct ifaddr *)dep[0]);
return dep[0];
}
if (dep[1]) {
ifa_ref((struct ifaddr *)dep[1]);
return dep[1];
}
return NULL;
}
/*
* perform DAD when interface becomes IFF_UP.
*/
void
in6_if_up(struct ifnet *ifp)
{
struct epoch_tracker et;
struct ifaddr *ifa;
struct in6_ifaddr *ia;
NET_EPOCH_ENTER(et);
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family != AF_INET6)
continue;
ia = (struct in6_ifaddr *)ifa;
if (ia->ia6_flags & IN6_IFF_TENTATIVE) {
/*
* The TENTATIVE flag was likely set by hand
* beforehand, implicitly indicating the need for DAD.
* We may be able to skip the random delay in this
* case, but we impose delays just in case.
*/
nd6_dad_start(ifa,
arc4random() % (MAX_RTR_SOLICITATION_DELAY * hz));
}
}
NET_EPOCH_EXIT(et);
/*
* special cases, like 6to4, are handled in in6_ifattach
*/
in6_ifattach(ifp, NULL);
}
int
in6if_do_dad(struct ifnet *ifp)
{
if ((ifp->if_flags & IFF_LOOPBACK) != 0)
return (0);
if ((ifp->if_flags & IFF_MULTICAST) == 0)
return (0);
if ((ND_IFINFO(ifp)->flags &
(ND6_IFF_IFDISABLED | ND6_IFF_NO_DAD)) != 0)
return (0);
return (1);
}
/*
* Calculate max IPv6 MTU through all the interfaces and store it
* to in6_maxmtu.
*/
void
in6_setmaxmtu(void)
{
struct epoch_tracker et;
unsigned long maxmtu = 0;
struct ifnet *ifp;
NET_EPOCH_ENTER(et);
CK_STAILQ_FOREACH(ifp, &V_ifnet, if_link) {
/* this function can be called during ifnet initialization */
if (!ifp->if_afdata[AF_INET6])
continue;
if ((ifp->if_flags & IFF_LOOPBACK) == 0 &&
IN6_LINKMTU(ifp) > maxmtu)
maxmtu = IN6_LINKMTU(ifp);
}
NET_EPOCH_EXIT(et);
if (maxmtu) /* update only when maxmtu is positive */
V_in6_maxmtu = maxmtu;
}
/*
* Provide the length of interface identifiers to be used for the link attached
* to the given interface. The length should be defined in "IPv6 over
* xxx-link" document. Note that address architecture might also define
* the length for a particular set of address prefixes, regardless of the
* link type. As clarified in rfc2462bis, those two definitions should be
* consistent, and those really are as of August 2004.
*/
int
in6_if2idlen(struct ifnet *ifp)
{
switch (ifp->if_type) {
case IFT_ETHER: /* RFC2464 */
case IFT_PROPVIRTUAL: /* XXX: no RFC. treat it as ether */
case IFT_L2VLAN: /* ditto */
case IFT_BRIDGE: /* bridge(4) only does Ethernet-like links */
case IFT_INFINIBAND:
return (64);
case IFT_PPP: /* RFC2472 */
return (64);
case IFT_FRELAY: /* RFC2590 */
return (64);
case IFT_IEEE1394: /* RFC3146 */
return (64);
case IFT_GIF:
return (64); /* draft-ietf-v6ops-mech-v2-07 */
case IFT_LOOP:
return (64); /* XXX: is this really correct? */
default:
/*
* Unknown link type:
* It might be controversial to use the today's common constant
* of 64 for these cases unconditionally. For full compliance,
* we should return an error in this case. On the other hand,
* if we simply miss the standard for the link type or a new
* standard is defined for a new link type, the IFID length
* is very likely to be the common constant. As a compromise,
* we always use the constant, but make an explicit notice
* indicating the "unknown" case.
*/
printf("in6_if2idlen: unknown link type (%d)\n", ifp->if_type);
return (64);
}
}
struct in6_llentry {
struct llentry base;
};
#define IN6_LLTBL_DEFAULT_HSIZE 32
#define IN6_LLTBL_HASH(k, h) \
(((((((k >> 8) ^ k) >> 8) ^ k) >> 8) ^ k) & ((h) - 1))
/*
* Do actual deallocation of @lle.
*/
static void
in6_lltable_destroy_lle_unlocked(epoch_context_t ctx)
{
struct llentry *lle;
lle = __containerof(ctx, struct llentry, lle_epoch_ctx);
LLE_LOCK_DESTROY(lle);
LLE_REQ_DESTROY(lle);
free(lle, M_LLTABLE);
}
/*
* Called by LLE_FREE_LOCKED when number of references
* drops to zero.
*/
static void
in6_lltable_destroy_lle(struct llentry *lle)
{
LLE_WUNLOCK(lle);
NET_EPOCH_CALL(in6_lltable_destroy_lle_unlocked, &lle->lle_epoch_ctx);
}
static struct llentry *
in6_lltable_new(const struct in6_addr *addr6, u_int flags)
{
struct in6_llentry *lle;
lle = malloc(sizeof(struct in6_llentry), M_LLTABLE, M_NOWAIT | M_ZERO);
if (lle == NULL) /* NB: caller generates msg */
return NULL;
lle->base.r_l3addr.addr6 = *addr6;
lle->base.lle_refcnt = 1;
lle->base.lle_free = in6_lltable_destroy_lle;
LLE_LOCK_INIT(&lle->base);
LLE_REQ_INIT(&lle->base);
callout_init(&lle->base.lle_timer, 1);
return (&lle->base);
}
static int
in6_lltable_match_prefix(const struct sockaddr *saddr,
const struct sockaddr *smask, u_int flags, struct llentry *lle)
{
const struct in6_addr *addr, *mask, *lle_addr;
addr = &((const struct sockaddr_in6 *)saddr)->sin6_addr;
mask = &((const struct sockaddr_in6 *)smask)->sin6_addr;
lle_addr = &lle->r_l3addr.addr6;
if (IN6_ARE_MASKED_ADDR_EQUAL(lle_addr, addr, mask) == 0)
return (0);
if (lle->la_flags & LLE_IFADDR) {
/*
* Delete LLE_IFADDR records IFF address & flag matches.
* Note that addr is the interface address within prefix
* being matched.
*/
if (IN6_ARE_ADDR_EQUAL(addr, lle_addr) &&
(flags & LLE_STATIC) != 0)
return (1);
return (0);
}
/* flags & LLE_STATIC means deleting both dynamic and static entries */
if ((flags & LLE_STATIC) || !(lle->la_flags & LLE_STATIC))
return (1);
return (0);
}
static void
in6_lltable_free_entry(struct lltable *llt, struct llentry *lle)
{
struct ifnet *ifp;
LLE_WLOCK_ASSERT(lle);
KASSERT(llt != NULL, ("lltable is NULL"));
/* Unlink entry from table */
if ((lle->la_flags & LLE_LINKED) != 0) {
ifp = llt->llt_ifp;
IF_AFDATA_WLOCK_ASSERT(ifp);
lltable_unlink_entry(llt, lle);
}
llentry_free(lle);
}
static int
in6_lltable_rtcheck(struct ifnet *ifp,
u_int flags,
const struct sockaddr *l3addr)
{
const struct sockaddr_in6 *sin6;
struct nhop_object *nh;
struct in6_addr dst;
uint32_t scopeid;
char ip6buf[INET6_ADDRSTRLEN];
int fibnum;
NET_EPOCH_ASSERT();
KASSERT(l3addr->sa_family == AF_INET6,
("sin_family %d", l3addr->sa_family));
sin6 = (const struct sockaddr_in6 *)l3addr;
in6_splitscope(&sin6->sin6_addr, &dst, &scopeid);
fibnum = V_rt_add_addr_allfibs ? RT_DEFAULT_FIB : ifp->if_fib;
nh = fib6_lookup(fibnum, &dst, scopeid, NHR_NONE, 0);
if (nh && ((nh->nh_flags & NHF_GATEWAY) || nh->nh_ifp != ifp)) {
struct ifaddr *ifa;
/*
* Create an ND6 cache for an IPv6 neighbor
* that is not covered by our own prefix.
*/
ifa = ifaof_ifpforaddr(l3addr, ifp);
if (ifa != NULL) {
return 0;
}
log(LOG_INFO, "IPv6 address: \"%s\" is not on the network\n",
ip6_sprintf(ip6buf, &sin6->sin6_addr));
return EINVAL;
}
return 0;
}
/*
* Called by the datapath to indicate that the entry was used.
*/
static void
in6_lltable_mark_used(struct llentry *lle)
{
LLE_REQ_LOCK(lle);
lle->r_skip_req = 0;
/*
* Set the hit time so the callback function
* can determine the remaining time before
* transiting to the DELAY state.
*/
lle->lle_hittime = time_uptime;
LLE_REQ_UNLOCK(lle);
}
static inline uint32_t
in6_lltable_hash_dst(const struct in6_addr *dst, uint32_t hsize)
{
return (IN6_LLTBL_HASH(dst->s6_addr32[3], hsize));
}
static uint32_t
in6_lltable_hash(const struct llentry *lle, uint32_t hsize)
{
return (in6_lltable_hash_dst(&lle->r_l3addr.addr6, hsize));
}
static void
in6_lltable_fill_sa_entry(const struct llentry *lle, struct sockaddr *sa)
{
struct sockaddr_in6 *sin6;
sin6 = (struct sockaddr_in6 *)sa;
bzero(sin6, sizeof(*sin6));
sin6->sin6_family = AF_INET6;
sin6->sin6_len = sizeof(*sin6);
sin6->sin6_addr = lle->r_l3addr.addr6;
}
static inline struct llentry *
in6_lltable_find_dst(struct lltable *llt, const struct in6_addr *dst)
{
struct llentry *lle;
struct llentries *lleh;
u_int hashidx;
hashidx = in6_lltable_hash_dst(dst, llt->llt_hsize);
lleh = &llt->lle_head[hashidx];
CK_LIST_FOREACH(lle, lleh, lle_next) {
if (lle->la_flags & LLE_DELETED)
continue;
if (IN6_ARE_ADDR_EQUAL(&lle->r_l3addr.addr6, dst))
break;
}
return (lle);
}
static void
in6_lltable_delete_entry(struct lltable *llt, struct llentry *lle)
{
lle->la_flags |= LLE_DELETED;
EVENTHANDLER_INVOKE(lle_event, lle, LLENTRY_DELETED);
#ifdef DIAGNOSTIC
log(LOG_INFO, "ifaddr cache = %p is deleted\n", lle);
#endif
llentry_free(lle);
}
static struct llentry *
in6_lltable_alloc(struct lltable *llt, u_int flags,
const struct sockaddr *l3addr)
{
const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)l3addr;
struct ifnet *ifp = llt->llt_ifp;
struct llentry *lle;
char linkhdr[LLE_MAX_LINKHDR];
size_t linkhdrsize;
int lladdr_off;
KASSERT(l3addr->sa_family == AF_INET6,
("sin_family %d", l3addr->sa_family));
/*
* A route that covers the given address must have
* been installed 1st because we are doing a resolution,
* verify this.
*/
if (!(flags & LLE_IFADDR) &&
in6_lltable_rtcheck(ifp, flags, l3addr) != 0)
return (NULL);
lle = in6_lltable_new(&sin6->sin6_addr, flags);
if (lle == NULL) {
log(LOG_INFO, "lla_lookup: new lle malloc failed\n");
return (NULL);
}
lle->la_flags = flags;
if ((flags & LLE_IFADDR) == LLE_IFADDR) {
linkhdrsize = LLE_MAX_LINKHDR;
if (lltable_calc_llheader(ifp, AF_INET6, IF_LLADDR(ifp),
linkhdr, &linkhdrsize, &lladdr_off) != 0) {
NET_EPOCH_CALL(in6_lltable_destroy_lle_unlocked, &lle->lle_epoch_ctx);
return (NULL);
}
lltable_set_entry_addr(ifp, lle, linkhdr, linkhdrsize,
lladdr_off);
lle->la_flags |= LLE_STATIC;
}
if ((lle->la_flags & LLE_STATIC) != 0)
lle->ln_state = ND6_LLINFO_REACHABLE;
return (lle);
}
static struct llentry *
in6_lltable_lookup(struct lltable *llt, u_int flags,
const struct sockaddr *l3addr)
{
const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)l3addr;
struct llentry *lle;
IF_AFDATA_LOCK_ASSERT(llt->llt_ifp);
KASSERT(l3addr->sa_family == AF_INET6,
("sin_family %d", l3addr->sa_family));
KASSERT((flags & (LLE_UNLOCKED | LLE_EXCLUSIVE)) !=
(LLE_UNLOCKED | LLE_EXCLUSIVE),
("wrong lle request flags: %#x", flags));
lle = in6_lltable_find_dst(llt, &sin6->sin6_addr);
if (lle == NULL)
return (NULL);
if (flags & LLE_UNLOCKED)
return (lle);
if (flags & LLE_EXCLUSIVE)
LLE_WLOCK(lle);
else
LLE_RLOCK(lle);
/*
* If the afdata lock is not held, the LLE may have been unlinked while
* we were blocked on the LLE lock. Check for this case.
*/
if (__predict_false((lle->la_flags & LLE_LINKED) == 0)) {
if (flags & LLE_EXCLUSIVE)
LLE_WUNLOCK(lle);
else
LLE_RUNLOCK(lle);
return (NULL);
}
return (lle);
}
static int
in6_lltable_dump_entry(struct lltable *llt, struct llentry *lle,
struct sysctl_req *wr)
{
struct ifnet *ifp = llt->llt_ifp;
/* XXX stack use */
struct {
struct rt_msghdr rtm;
struct sockaddr_in6 sin6;
/*
* ndp.c assumes that sdl is word aligned
*/
#ifdef __LP64__
uint32_t pad;
#endif
struct sockaddr_dl sdl;
} ndpc;
struct sockaddr_dl *sdl;
int error;
bzero(&ndpc, sizeof(ndpc));
/* skip deleted entries */
if ((lle->la_flags & LLE_DELETED) == LLE_DELETED)
return (0);
/* Skip if jailed and not a valid IP of the prison. */
lltable_fill_sa_entry(lle, (struct sockaddr *)&ndpc.sin6);
if (prison_if(wr->td->td_ucred, (struct sockaddr *)&ndpc.sin6) != 0)
return (0);
/*
* produce a msg made of:
* struct rt_msghdr;
* struct sockaddr_in6 (IPv6)
* struct sockaddr_dl;
*/
ndpc.rtm.rtm_msglen = sizeof(ndpc);
ndpc.rtm.rtm_version = RTM_VERSION;
ndpc.rtm.rtm_type = RTM_GET;
ndpc.rtm.rtm_flags = RTF_UP;
ndpc.rtm.rtm_addrs = RTA_DST | RTA_GATEWAY;
sa6_recoverscope(&ndpc.sin6);
/* publish */
if (lle->la_flags & LLE_PUB)
ndpc.rtm.rtm_flags |= RTF_ANNOUNCE;
sdl = &ndpc.sdl;
sdl->sdl_family = AF_LINK;
sdl->sdl_len = sizeof(*sdl);
sdl->sdl_index = ifp->if_index;
sdl->sdl_type = ifp->if_type;
if ((lle->la_flags & LLE_VALID) == LLE_VALID) {
sdl->sdl_alen = ifp->if_addrlen;
bcopy(lle->ll_addr, LLADDR(sdl), ifp->if_addrlen);
} else {
sdl->sdl_alen = 0;
bzero(LLADDR(sdl), ifp->if_addrlen);
}
if (lle->la_expire != 0)
ndpc.rtm.rtm_rmx.rmx_expire = lle->la_expire +
lle->lle_remtime / hz + time_second - time_uptime;
ndpc.rtm.rtm_flags |= (RTF_HOST | RTF_LLDATA);
if (lle->la_flags & LLE_STATIC)
ndpc.rtm.rtm_flags |= RTF_STATIC;
if (lle->la_flags & LLE_IFADDR)
ndpc.rtm.rtm_flags |= RTF_PINNED;
if (lle->ln_router != 0)
ndpc.rtm.rtm_flags |= RTF_GATEWAY;
ndpc.rtm.rtm_rmx.rmx_pksent = lle->la_asked;
/* Store state in rmx_weight value */
ndpc.rtm.rtm_rmx.rmx_state = lle->ln_state;
ndpc.rtm.rtm_index = ifp->if_index;
error = SYSCTL_OUT(wr, &ndpc, sizeof(ndpc));
return (error);
}
static struct lltable *
in6_lltattach(struct ifnet *ifp)
{
struct lltable *llt;
llt = lltable_allocate_htbl(IN6_LLTBL_DEFAULT_HSIZE);
llt->llt_af = AF_INET6;
llt->llt_ifp = ifp;
llt->llt_lookup = in6_lltable_lookup;
llt->llt_alloc_entry = in6_lltable_alloc;
llt->llt_delete_entry = in6_lltable_delete_entry;
llt->llt_dump_entry = in6_lltable_dump_entry;
llt->llt_hash = in6_lltable_hash;
llt->llt_fill_sa_entry = in6_lltable_fill_sa_entry;
llt->llt_free_entry = in6_lltable_free_entry;
llt->llt_match_prefix = in6_lltable_match_prefix;
llt->llt_mark_used = in6_lltable_mark_used;
lltable_link(llt);
return (llt);
}
void *
in6_domifattach(struct ifnet *ifp)
{
struct in6_ifextra *ext;
/* There are not IPv6-capable interfaces. */
switch (ifp->if_type) {
case IFT_PFLOG:
case IFT_PFSYNC:
case IFT_USB:
return (NULL);
}
ext = (struct in6_ifextra *)malloc(sizeof(*ext), M_IFADDR, M_WAITOK);
bzero(ext, sizeof(*ext));
ext->in6_ifstat = malloc(sizeof(counter_u64_t) *
sizeof(struct in6_ifstat) / sizeof(uint64_t), M_IFADDR, M_WAITOK);
COUNTER_ARRAY_ALLOC(ext->in6_ifstat,
sizeof(struct in6_ifstat) / sizeof(uint64_t), M_WAITOK);
ext->icmp6_ifstat = malloc(sizeof(counter_u64_t) *
sizeof(struct icmp6_ifstat) / sizeof(uint64_t), M_IFADDR,
M_WAITOK);
COUNTER_ARRAY_ALLOC(ext->icmp6_ifstat,
sizeof(struct icmp6_ifstat) / sizeof(uint64_t), M_WAITOK);
ext->nd_ifinfo = nd6_ifattach(ifp);
ext->scope6_id = scope6_ifattach(ifp);
ext->lltable = in6_lltattach(ifp);
ext->mld_ifinfo = mld_domifattach(ifp);
return ext;
}
int
in6_domifmtu(struct ifnet *ifp)
{
if (ifp->if_afdata[AF_INET6] == NULL)
return ifp->if_mtu;
return (IN6_LINKMTU(ifp));
}
void
in6_domifdetach(struct ifnet *ifp, void *aux)
{
struct in6_ifextra *ext = (struct in6_ifextra *)aux;
mld_domifdetach(ifp);
scope6_ifdetach(ext->scope6_id);
nd6_ifdetach(ifp, ext->nd_ifinfo);
lltable_free(ext->lltable);
COUNTER_ARRAY_FREE(ext->in6_ifstat,
sizeof(struct in6_ifstat) / sizeof(uint64_t));
free(ext->in6_ifstat, M_IFADDR);
COUNTER_ARRAY_FREE(ext->icmp6_ifstat,
sizeof(struct icmp6_ifstat) / sizeof(uint64_t));
free(ext->icmp6_ifstat, M_IFADDR);
free(ext, M_IFADDR);
}
/*
* Convert sockaddr_in6 to sockaddr_in. Original sockaddr_in6 must be
* v4 mapped addr or v4 compat addr
*/
void
in6_sin6_2_sin(struct sockaddr_in *sin, struct sockaddr_in6 *sin6)
{
bzero(sin, sizeof(*sin));
sin->sin_len = sizeof(struct sockaddr_in);
sin->sin_family = AF_INET;
sin->sin_port = sin6->sin6_port;
sin->sin_addr.s_addr = sin6->sin6_addr.s6_addr32[3];
}
/* Convert sockaddr_in to sockaddr_in6 in v4 mapped addr format. */
void
in6_sin_2_v4mapsin6(struct sockaddr_in *sin, struct sockaddr_in6 *sin6)
{
bzero(sin6, sizeof(*sin6));
sin6->sin6_len = sizeof(struct sockaddr_in6);
sin6->sin6_family = AF_INET6;
sin6->sin6_port = sin->sin_port;
sin6->sin6_addr.s6_addr32[0] = 0;
sin6->sin6_addr.s6_addr32[1] = 0;
sin6->sin6_addr.s6_addr32[2] = IPV6_ADDR_INT32_SMP;
sin6->sin6_addr.s6_addr32[3] = sin->sin_addr.s_addr;
}
/* Convert sockaddr_in6 into sockaddr_in. */
void
in6_sin6_2_sin_in_sock(struct sockaddr *nam)
{
struct sockaddr_in *sin_p;
struct sockaddr_in6 sin6;
/*
* Save original sockaddr_in6 addr and convert it
* to sockaddr_in.
*/
sin6 = *(struct sockaddr_in6 *)nam;
sin_p = (struct sockaddr_in *)nam;
in6_sin6_2_sin(sin_p, &sin6);
}
/* Convert sockaddr_in into sockaddr_in6 in v4 mapped addr format. */
void
in6_sin_2_v4mapsin6_in_sock(struct sockaddr **nam)
{
struct sockaddr_in *sin_p;
struct sockaddr_in6 *sin6_p;
sin6_p = malloc(sizeof *sin6_p, M_SONAME, M_WAITOK);
sin_p = (struct sockaddr_in *)*nam;
in6_sin_2_v4mapsin6(sin_p, sin6_p);
free(*nam, M_SONAME);
*nam = (struct sockaddr *)sin6_p;
}
diff --git a/sys/netinet6/nd6_rtr.c b/sys/netinet6/nd6_rtr.c
index c6317b1ea263..eca704dc2843 100644
--- a/sys/netinet6/nd6_rtr.c
+++ b/sys/netinet6/nd6_rtr.c
@@ -1,2626 +1,2579 @@
/*-
* SPDX-License-Identifier: BSD-3-Clause
*
* 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.
*
* $KAME: nd6_rtr.c,v 1.111 2001/04/27 01:37:15 jinmei Exp $
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_inet.h"
#include "opt_inet6.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/refcount.h>
#include <sys/socket.h>
#include <sys/sockio.h>
#include <sys/time.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/errno.h>
#include <sys/rmlock.h>
#include <sys/rwlock.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>
#include <sys/queue.h>
#include <net/if.h>
#include <net/if_var.h>
#include <net/if_types.h>
#include <net/if_dl.h>
#include <net/route.h>
#include <net/route/nhop.h>
#include <net/route/route_ctl.h>
#include <net/route/route_var.h>
#include <net/radix.h>
#include <net/vnet.h>
#include <netinet/in.h>
#include <net/if_llatbl.h>
#include <netinet6/in6_var.h>
#include <netinet6/in6_ifattach.h>
#include <netinet/ip6.h>
#include <netinet6/ip6_var.h>
#include <netinet6/nd6.h>
#include <netinet/icmp6.h>
#include <netinet6/scope6_var.h>
static struct nd_defrouter *defrtrlist_update(struct nd_defrouter *);
static int prelist_update(struct nd_prefixctl *, struct nd_defrouter *,
struct mbuf *, int);
static int nd6_prefix_onlink(struct nd_prefix *);
TAILQ_HEAD(nd6_drhead, nd_defrouter);
VNET_DEFINE_STATIC(struct nd6_drhead, nd6_defrouter);
#define V_nd6_defrouter VNET(nd6_defrouter)
VNET_DECLARE(int, nd6_recalc_reachtm_interval);
#define V_nd6_recalc_reachtm_interval VNET(nd6_recalc_reachtm_interval)
VNET_DEFINE_STATIC(struct ifnet *, nd6_defifp);
VNET_DEFINE(int, nd6_defifindex);
#define V_nd6_defifp VNET(nd6_defifp)
VNET_DEFINE(int, ip6_use_tempaddr) = 0;
VNET_DEFINE(int, ip6_desync_factor);
VNET_DEFINE(u_int32_t, ip6_temp_preferred_lifetime) = DEF_TEMP_PREFERRED_LIFETIME;
VNET_DEFINE(u_int32_t, ip6_temp_valid_lifetime) = DEF_TEMP_VALID_LIFETIME;
VNET_DEFINE(int, ip6_temp_regen_advance) = TEMPADDR_REGEN_ADVANCE;
#ifdef EXPERIMENTAL
VNET_DEFINE(int, nd6_ignore_ipv6_only_ra) = 1;
#endif
SYSCTL_DECL(_net_inet6_icmp6);
/* RTPREF_MEDIUM has to be 0! */
#define RTPREF_HIGH 1
#define RTPREF_MEDIUM 0
#define RTPREF_LOW (-1)
#define RTPREF_RESERVED (-2)
#define RTPREF_INVALID (-3) /* internal */
static void
defrouter_ref(struct nd_defrouter *dr)
{
refcount_acquire(&dr->refcnt);
}
void
defrouter_rele(struct nd_defrouter *dr)
{
if (refcount_release(&dr->refcnt))
free(dr, M_IP6NDP);
}
/*
* Remove a router from the global list and optionally stash it in a
* caller-supplied queue.
*/
static void
defrouter_unlink(struct nd_defrouter *dr, struct nd6_drhead *drq)
{
ND6_WLOCK_ASSERT();
TAILQ_REMOVE(&V_nd6_defrouter, dr, dr_entry);
V_nd6_list_genid++;
if (drq != NULL)
TAILQ_INSERT_TAIL(drq, dr, dr_entry);
}
/*
* Receive Router Solicitation Message - just for routers.
* Router solicitation/advertisement is mostly managed by userland program
* (rtadvd) so here we have no function like nd6_ra_output().
*
* Based on RFC 2461
*/
void
nd6_rs_input(struct mbuf *m, int off, int icmp6len)
{
struct ifnet *ifp;
struct ip6_hdr *ip6;
struct nd_router_solicit *nd_rs;
struct in6_addr saddr6;
union nd_opts ndopts;
char ip6bufs[INET6_ADDRSTRLEN], ip6bufd[INET6_ADDRSTRLEN];
char *lladdr;
int lladdrlen;
ifp = m->m_pkthdr.rcvif;
/*
* Accept RS only when V_ip6_forwarding=1 and the interface has
* no ND6_IFF_ACCEPT_RTADV.
*/
if (!V_ip6_forwarding || ND_IFINFO(ifp)->flags & ND6_IFF_ACCEPT_RTADV)
goto freeit;
/* RFC 6980: Nodes MUST silently ignore fragments */
if(m->m_flags & M_FRAGMENTED)
goto freeit;
/* Sanity checks */
ip6 = mtod(m, struct ip6_hdr *);
if (__predict_false(ip6->ip6_hlim != 255)) {
ICMP6STAT_INC(icp6s_invlhlim);
nd6log((LOG_ERR,
"%s: invalid hlim (%d) from %s to %s on %s\n", __func__,
ip6->ip6_hlim, ip6_sprintf(ip6bufs, &ip6->ip6_src),
ip6_sprintf(ip6bufd, &ip6->ip6_dst), if_name(ifp)));
goto bad;
}
/*
* Don't update the neighbor cache, if src = ::.
* This indicates that the src has no IP address assigned yet.
*/
saddr6 = ip6->ip6_src;
if (IN6_IS_ADDR_UNSPECIFIED(&saddr6))
goto freeit;
if (m->m_len < off + icmp6len) {
m = m_pullup(m, off + icmp6len);
if (m == NULL) {
IP6STAT_INC(ip6s_exthdrtoolong);
return;
}
}
ip6 = mtod(m, struct ip6_hdr *);
nd_rs = (struct nd_router_solicit *)((caddr_t)ip6 + off);
icmp6len -= sizeof(*nd_rs);
nd6_option_init(nd_rs + 1, icmp6len, &ndopts);
if (nd6_options(&ndopts) < 0) {
nd6log((LOG_INFO,
"%s: invalid ND option, ignored\n", __func__));
/* nd6_options have incremented stats */
goto freeit;
}
lladdr = NULL;
lladdrlen = 0;
if (ndopts.nd_opts_src_lladdr) {
lladdr = (char *)(ndopts.nd_opts_src_lladdr + 1);
lladdrlen = ndopts.nd_opts_src_lladdr->nd_opt_len << 3;
}
if (lladdr && ((ifp->if_addrlen + 2 + 7) & ~7) != lladdrlen) {
nd6log((LOG_INFO,
"%s: lladdrlen mismatch for %s (if %d, RS packet %d)\n",
__func__, ip6_sprintf(ip6bufs, &saddr6),
ifp->if_addrlen, lladdrlen - 2));
goto bad;
}
nd6_cache_lladdr(ifp, &saddr6, lladdr, lladdrlen, ND_ROUTER_SOLICIT, 0);
freeit:
m_freem(m);
return;
bad:
ICMP6STAT_INC(icp6s_badrs);
m_freem(m);
}
#ifdef EXPERIMENTAL
/*
* An initial update routine for draft-ietf-6man-ipv6only-flag.
* We need to iterate over all default routers for the given
* interface to see whether they are all advertising the "S"
* (IPv6-Only) flag. If they do set, otherwise unset, the
* interface flag we later use to filter on.
*/
static void
defrtr_ipv6_only_ifp(struct ifnet *ifp)
{
struct nd_defrouter *dr;
bool ipv6_only, ipv6_only_old;
#ifdef INET
struct epoch_tracker et;
struct ifaddr *ifa;
bool has_ipv4_addr;
#endif
if (V_nd6_ignore_ipv6_only_ra != 0)
return;
ipv6_only = true;
ND6_RLOCK();
TAILQ_FOREACH(dr, &V_nd6_defrouter, dr_entry)
if (dr->ifp == ifp &&
(dr->raflags & ND_RA_FLAG_IPV6_ONLY) == 0)
ipv6_only = false;
ND6_RUNLOCK();
IF_AFDATA_WLOCK(ifp);
ipv6_only_old = ND_IFINFO(ifp)->flags & ND6_IFF_IPV6_ONLY;
IF_AFDATA_WUNLOCK(ifp);
/* If nothing changed, we have an early exit. */
if (ipv6_only == ipv6_only_old)
return;
#ifdef INET
/*
* Should we want to set the IPV6-ONLY flag, check if the
* interface has a non-0/0 and non-link-local IPv4 address
* configured on it. If it has we will assume working
* IPv4 operations and will clear the interface flag.
*/
has_ipv4_addr = false;
if (ipv6_only) {
NET_EPOCH_ENTER(et);
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family != AF_INET)
continue;
if (in_canforward(
satosin(ifa->ifa_addr)->sin_addr)) {
has_ipv4_addr = true;
break;
}
}
NET_EPOCH_EXIT(et);
}
if (ipv6_only && has_ipv4_addr) {
log(LOG_NOTICE, "%s rcvd RA w/ IPv6-Only flag set but has IPv4 "
"configured, ignoring IPv6-Only flag.\n", ifp->if_xname);
ipv6_only = false;
}
#endif
IF_AFDATA_WLOCK(ifp);
if (ipv6_only)
ND_IFINFO(ifp)->flags |= ND6_IFF_IPV6_ONLY;
else
ND_IFINFO(ifp)->flags &= ~ND6_IFF_IPV6_ONLY;
IF_AFDATA_WUNLOCK(ifp);
#ifdef notyet
/* Send notification of flag change. */
#endif
}
static void
defrtr_ipv6_only_ipf_down(struct ifnet *ifp)
{
IF_AFDATA_WLOCK(ifp);
ND_IFINFO(ifp)->flags &= ~ND6_IFF_IPV6_ONLY;
IF_AFDATA_WUNLOCK(ifp);
}
#endif /* EXPERIMENTAL */
void
nd6_ifnet_link_event(void *arg __unused, struct ifnet *ifp, int linkstate)
{
/*
* XXX-BZ we might want to trigger re-evaluation of our default router
* availability. E.g., on link down the default router might be
* unreachable but a different interface might still have connectivity.
*/
#ifdef EXPERIMENTAL
if (linkstate == LINK_STATE_DOWN)
defrtr_ipv6_only_ipf_down(ifp);
#endif
}
/*
* Receive Router Advertisement Message.
*
* Based on RFC 2461
* TODO: on-link bit on prefix information
* TODO: ND_RA_FLAG_{OTHER,MANAGED} processing
*/
void
nd6_ra_input(struct mbuf *m, int off, int icmp6len)
{
struct ifnet *ifp;
struct nd_ifinfo *ndi;
struct ip6_hdr *ip6;
struct nd_router_advert *nd_ra;
struct in6_addr saddr6;
struct nd_defrouter *dr;
union nd_opts ndopts;
char ip6bufs[INET6_ADDRSTRLEN], ip6bufd[INET6_ADDRSTRLEN];
int mcast;
/*
* We only accept RAs only when the per-interface flag
* ND6_IFF_ACCEPT_RTADV is on the receiving interface.
*/
ifp = m->m_pkthdr.rcvif;
ndi = ND_IFINFO(ifp);
if (!(ndi->flags & ND6_IFF_ACCEPT_RTADV))
goto freeit;
/* RFC 6980: Nodes MUST silently ignore fragments */
if(m->m_flags & M_FRAGMENTED)
goto freeit;
ip6 = mtod(m, struct ip6_hdr *);
if (__predict_false(ip6->ip6_hlim != 255)) {
ICMP6STAT_INC(icp6s_invlhlim);
nd6log((LOG_ERR,
"%s: invalid hlim (%d) from %s to %s on %s\n", __func__,
ip6->ip6_hlim, ip6_sprintf(ip6bufs, &ip6->ip6_src),
ip6_sprintf(ip6bufd, &ip6->ip6_dst), if_name(ifp)));
goto bad;
}
saddr6 = ip6->ip6_src;
if (!IN6_IS_ADDR_LINKLOCAL(&saddr6)) {
nd6log((LOG_ERR,
"%s: src %s is not link-local\n", __func__,
ip6_sprintf(ip6bufs, &saddr6)));
goto bad;
}
if (m->m_len < off + icmp6len) {
m = m_pullup(m, off + icmp6len);
if (m == NULL) {
IP6STAT_INC(ip6s_exthdrtoolong);
return;
}
}
ip6 = mtod(m, struct ip6_hdr *);
nd_ra = (struct nd_router_advert *)((caddr_t)ip6 + off);
icmp6len -= sizeof(*nd_ra);
nd6_option_init(nd_ra + 1, icmp6len, &ndopts);
if (nd6_options(&ndopts) < 0) {
nd6log((LOG_INFO,
"%s: invalid ND option, ignored\n", __func__));
/* nd6_options have incremented stats */
goto freeit;
}
mcast = 0;
dr = NULL;
{
struct nd_defrouter dr0;
u_int32_t advreachable = nd_ra->nd_ra_reachable;
/* remember if this is a multicasted advertisement */
if (IN6_IS_ADDR_MULTICAST(&ip6->ip6_dst))
mcast = 1;
bzero(&dr0, sizeof(dr0));
dr0.rtaddr = saddr6;
dr0.raflags = nd_ra->nd_ra_flags_reserved;
/*
* Effectively-disable routes from RA messages when
* ND6_IFF_NO_RADR enabled on the receiving interface or
* (ip6.forwarding == 1 && ip6.rfc6204w3 != 1).
*/
if (ndi->flags & ND6_IFF_NO_RADR)
dr0.rtlifetime = 0;
else if (V_ip6_forwarding && !V_ip6_rfc6204w3)
dr0.rtlifetime = 0;
else
dr0.rtlifetime = ntohs(nd_ra->nd_ra_router_lifetime);
dr0.expire = time_uptime + dr0.rtlifetime;
dr0.ifp = ifp;
/* unspecified or not? (RFC 2461 6.3.4) */
if (advreachable) {
advreachable = ntohl(advreachable);
if (advreachable <= MAX_REACHABLE_TIME &&
ndi->basereachable != advreachable) {
ndi->basereachable = advreachable;
ndi->reachable = ND_COMPUTE_RTIME(ndi->basereachable);
ndi->recalctm = V_nd6_recalc_reachtm_interval; /* reset */
}
}
if (nd_ra->nd_ra_retransmit)
ndi->retrans = ntohl(nd_ra->nd_ra_retransmit);
if (nd_ra->nd_ra_curhoplimit) {
if (ndi->chlim < nd_ra->nd_ra_curhoplimit)
ndi->chlim = nd_ra->nd_ra_curhoplimit;
else if (ndi->chlim != nd_ra->nd_ra_curhoplimit) {
log(LOG_ERR, "RA with a lower CurHopLimit sent from "
"%s on %s (current = %d, received = %d). "
"Ignored.\n", ip6_sprintf(ip6bufs, &ip6->ip6_src),
if_name(ifp), ndi->chlim, nd_ra->nd_ra_curhoplimit);
}
}
dr = defrtrlist_update(&dr0);
#ifdef EXPERIMENTAL
defrtr_ipv6_only_ifp(ifp);
#endif
}
/*
* prefix
*/
if (ndopts.nd_opts_pi) {
struct nd_opt_hdr *pt;
struct nd_opt_prefix_info *pi = NULL;
struct nd_prefixctl pr;
for (pt = (struct nd_opt_hdr *)ndopts.nd_opts_pi;
pt <= (struct nd_opt_hdr *)ndopts.nd_opts_pi_end;
pt = (struct nd_opt_hdr *)((caddr_t)pt +
(pt->nd_opt_len << 3))) {
if (pt->nd_opt_type != ND_OPT_PREFIX_INFORMATION)
continue;
pi = (struct nd_opt_prefix_info *)pt;
if (pi->nd_opt_pi_len != 4) {
nd6log((LOG_INFO,
"%s: invalid option len %d for prefix "
"information option, ignored\n", __func__,
pi->nd_opt_pi_len));
continue;
}
if (128 < pi->nd_opt_pi_prefix_len) {
nd6log((LOG_INFO,
"%s: invalid prefix len %d for prefix "
"information option, ignored\n", __func__,
pi->nd_opt_pi_prefix_len));
continue;
}
if (IN6_IS_ADDR_MULTICAST(&pi->nd_opt_pi_prefix)
|| IN6_IS_ADDR_LINKLOCAL(&pi->nd_opt_pi_prefix)) {
nd6log((LOG_INFO,
"%s: invalid prefix %s, ignored\n",
__func__, ip6_sprintf(ip6bufs,
&pi->nd_opt_pi_prefix)));
continue;
}
bzero(&pr, sizeof(pr));
pr.ndpr_prefix.sin6_family = AF_INET6;
pr.ndpr_prefix.sin6_len = sizeof(pr.ndpr_prefix);
pr.ndpr_prefix.sin6_addr = pi->nd_opt_pi_prefix;
pr.ndpr_ifp = (struct ifnet *)m->m_pkthdr.rcvif;
pr.ndpr_raf_onlink = (pi->nd_opt_pi_flags_reserved &
ND_OPT_PI_FLAG_ONLINK) ? 1 : 0;
pr.ndpr_raf_auto = (pi->nd_opt_pi_flags_reserved &
ND_OPT_PI_FLAG_AUTO) ? 1 : 0;
pr.ndpr_plen = pi->nd_opt_pi_prefix_len;
pr.ndpr_vltime = ntohl(pi->nd_opt_pi_valid_time);
pr.ndpr_pltime = ntohl(pi->nd_opt_pi_preferred_time);
(void)prelist_update(&pr, dr, m, mcast);
}
}
if (dr != NULL) {
defrouter_rele(dr);
dr = NULL;
}
/*
* MTU
*/
if (ndopts.nd_opts_mtu && ndopts.nd_opts_mtu->nd_opt_mtu_len == 1) {
u_long mtu;
u_long maxmtu;
mtu = (u_long)ntohl(ndopts.nd_opts_mtu->nd_opt_mtu_mtu);
/* lower bound */
if (mtu < IPV6_MMTU) {
nd6log((LOG_INFO, "%s: bogus mtu option mtu=%lu sent "
"from %s, ignoring\n", __func__,
mtu, ip6_sprintf(ip6bufs, &ip6->ip6_src)));
goto skip;
}
/* upper bound */
maxmtu = (ndi->maxmtu && ndi->maxmtu < ifp->if_mtu)
? ndi->maxmtu : ifp->if_mtu;
if (mtu <= maxmtu) {
int change = (ndi->linkmtu != mtu);
ndi->linkmtu = mtu;
if (change) {
/* in6_maxmtu may change */
in6_setmaxmtu();
rt_updatemtu(ifp);
}
} else {
nd6log((LOG_INFO, "%s: bogus mtu=%lu sent from %s; "
"exceeds maxmtu %lu, ignoring\n", __func__,
mtu, ip6_sprintf(ip6bufs, &ip6->ip6_src), maxmtu));
}
}
skip:
/*
* Source link layer address
*/
{
char *lladdr = NULL;
int lladdrlen = 0;
if (ndopts.nd_opts_src_lladdr) {
lladdr = (char *)(ndopts.nd_opts_src_lladdr + 1);
lladdrlen = ndopts.nd_opts_src_lladdr->nd_opt_len << 3;
}
if (lladdr && ((ifp->if_addrlen + 2 + 7) & ~7) != lladdrlen) {
nd6log((LOG_INFO,
"%s: lladdrlen mismatch for %s (if %d, RA packet %d)\n",
__func__, ip6_sprintf(ip6bufs, &saddr6),
ifp->if_addrlen, lladdrlen - 2));
goto bad;
}
nd6_cache_lladdr(ifp, &saddr6, lladdr,
lladdrlen, ND_ROUTER_ADVERT, 0);
/*
* Installing a link-layer address might change the state of the
* router's neighbor cache, which might also affect our on-link
* detection of adveritsed prefixes.
*/
pfxlist_onlink_check();
}
freeit:
m_freem(m);
return;
bad:
ICMP6STAT_INC(icp6s_badra);
m_freem(m);
}
/* PFXRTR */
static struct nd_pfxrouter *
pfxrtr_lookup(struct nd_prefix *pr, struct nd_defrouter *dr)
{
struct nd_pfxrouter *search;
ND6_LOCK_ASSERT();
LIST_FOREACH(search, &pr->ndpr_advrtrs, pfr_entry) {
if (search->router == dr)
break;
}
return (search);
}
static void
pfxrtr_add(struct nd_prefix *pr, struct nd_defrouter *dr)
{
struct nd_pfxrouter *new;
bool update;
ND6_UNLOCK_ASSERT();
ND6_RLOCK();
if (pfxrtr_lookup(pr, dr) != NULL) {
ND6_RUNLOCK();
return;
}
ND6_RUNLOCK();
new = malloc(sizeof(*new), M_IP6NDP, M_NOWAIT | M_ZERO);
if (new == NULL)
return;
defrouter_ref(dr);
new->router = dr;
ND6_WLOCK();
if (pfxrtr_lookup(pr, dr) == NULL) {
LIST_INSERT_HEAD(&pr->ndpr_advrtrs, new, pfr_entry);
update = true;
} else {
/* We lost a race to add the reference. */
defrouter_rele(dr);
free(new, M_IP6NDP);
update = false;
}
ND6_WUNLOCK();
if (update)
pfxlist_onlink_check();
}
static void
pfxrtr_del(struct nd_pfxrouter *pfr)
{
ND6_WLOCK_ASSERT();
LIST_REMOVE(pfr, pfr_entry);
defrouter_rele(pfr->router);
free(pfr, M_IP6NDP);
}
/* Default router list processing sub routines. */
static void
defrouter_addreq(struct nd_defrouter *new)
{
struct sockaddr_in6 def, mask, gate;
struct rt_addrinfo info;
struct rib_cmd_info rc;
unsigned int fibnum;
int error;
bzero(&def, sizeof(def));
bzero(&mask, sizeof(mask));
bzero(&gate, sizeof(gate));
def.sin6_len = mask.sin6_len = gate.sin6_len =
sizeof(struct sockaddr_in6);
def.sin6_family = gate.sin6_family = AF_INET6;
gate.sin6_addr = new->rtaddr;
fibnum = new->ifp->if_fib;
bzero((caddr_t)&info, sizeof(info));
info.rti_flags = RTF_GATEWAY;
info.rti_info[RTAX_DST] = (struct sockaddr *)&def;
info.rti_info[RTAX_GATEWAY] = (struct sockaddr *)&gate;
info.rti_info[RTAX_NETMASK] = (struct sockaddr *)&mask;
NET_EPOCH_ASSERT();
error = rib_action(fibnum, RTM_ADD, &info, &rc);
if (rc.rc_rt != NULL) {
struct nhop_object *nh = nhop_select(rc.rc_nh_new, 0);
rt_routemsg(RTM_ADD, rc.rc_rt, nh, fibnum);
}
if (error == 0)
new->installed = 1;
}
/*
* Remove the default route for a given router.
* This is just a subroutine function for defrouter_select_fib(), and
* should not be called from anywhere else.
*/
static void
defrouter_delreq(struct nd_defrouter *dr)
{
struct sockaddr_in6 def, mask, gate;
struct rt_addrinfo info;
struct rib_cmd_info rc;
struct epoch_tracker et;
unsigned int fibnum;
bzero(&def, sizeof(def));
bzero(&mask, sizeof(mask));
bzero(&gate, sizeof(gate));
def.sin6_len = mask.sin6_len = gate.sin6_len =
sizeof(struct sockaddr_in6);
def.sin6_family = gate.sin6_family = AF_INET6;
gate.sin6_addr = dr->rtaddr;
fibnum = dr->ifp->if_fib;
bzero((caddr_t)&info, sizeof(info));
info.rti_flags = RTF_GATEWAY;
info.rti_info[RTAX_DST] = (struct sockaddr *)&def;
info.rti_info[RTAX_GATEWAY] = (struct sockaddr *)&gate;
info.rti_info[RTAX_NETMASK] = (struct sockaddr *)&mask;
NET_EPOCH_ENTER(et);
rib_action(fibnum, RTM_DELETE, &info, &rc);
if (rc.rc_rt != NULL) {
struct nhop_object *nh = nhop_select(rc.rc_nh_old, 0);
rt_routemsg(RTM_DELETE, rc.rc_rt, nh, fibnum);
}
NET_EPOCH_EXIT(et);
dr->installed = 0;
}
static void
defrouter_del(struct nd_defrouter *dr)
{
struct nd_defrouter *deldr = NULL;
struct nd_prefix *pr;
struct nd_pfxrouter *pfxrtr;
ND6_UNLOCK_ASSERT();
/*
* Flush all the routing table entries that use the router
* as a next hop.
*/
if (ND_IFINFO(dr->ifp)->flags & ND6_IFF_ACCEPT_RTADV)
rt6_flush(&dr->rtaddr, dr->ifp);
#ifdef EXPERIMENTAL
defrtr_ipv6_only_ifp(dr->ifp);
#endif
if (dr->installed) {
deldr = dr;
defrouter_delreq(dr);
}
/*
* Also delete all the pointers to the router in each prefix lists.
*/
ND6_WLOCK();
LIST_FOREACH(pr, &V_nd_prefix, ndpr_entry) {
if ((pfxrtr = pfxrtr_lookup(pr, dr)) != NULL)
pfxrtr_del(pfxrtr);
}
ND6_WUNLOCK();
pfxlist_onlink_check();
/*
* If the router is the primary one, choose a new one.
* Note that defrouter_select_fib() will remove the current
* gateway from the routing table.
*/
if (deldr)
defrouter_select_fib(deldr->ifp->if_fib);
/*
* Release the list reference.
*/
defrouter_rele(dr);
}
struct nd_defrouter *
defrouter_lookup_locked(const struct in6_addr *addr, struct ifnet *ifp)
{
struct nd_defrouter *dr;
ND6_LOCK_ASSERT();
TAILQ_FOREACH(dr, &V_nd6_defrouter, dr_entry)
if (dr->ifp == ifp && IN6_ARE_ADDR_EQUAL(addr, &dr->rtaddr)) {
defrouter_ref(dr);
return (dr);
}
return (NULL);
}
struct nd_defrouter *
defrouter_lookup(const struct in6_addr *addr, struct ifnet *ifp)
{
struct nd_defrouter *dr;
ND6_RLOCK();
dr = defrouter_lookup_locked(addr, ifp);
ND6_RUNLOCK();
return (dr);
}
/*
* Remove all default routes from default router list.
*/
void
defrouter_reset(void)
{
struct nd_defrouter *dr, **dra;
int count, i;
count = i = 0;
/*
* We can't delete routes with the ND lock held, so make a copy of the
* current default router list and use that when deleting routes.
*/
ND6_RLOCK();
TAILQ_FOREACH(dr, &V_nd6_defrouter, dr_entry)
count++;
ND6_RUNLOCK();
dra = malloc(count * sizeof(*dra), M_TEMP, M_WAITOK | M_ZERO);
ND6_RLOCK();
TAILQ_FOREACH(dr, &V_nd6_defrouter, dr_entry) {
if (i == count)
break;
defrouter_ref(dr);
dra[i++] = dr;
}
ND6_RUNLOCK();
for (i = 0; i < count && dra[i] != NULL; i++) {
defrouter_delreq(dra[i]);
defrouter_rele(dra[i]);
}
free(dra, M_TEMP);
/*
* XXX should we also nuke any default routers in the kernel, by
* going through them by rtalloc1()?
*/
}
/*
* Look up a matching default router list entry and remove it. Returns true if a
* matching entry was found, false otherwise.
*/
bool
defrouter_remove(struct in6_addr *addr, struct ifnet *ifp)
{
struct nd_defrouter *dr;
ND6_WLOCK();
dr = defrouter_lookup_locked(addr, ifp);
if (dr == NULL) {
ND6_WUNLOCK();
return (false);
}
defrouter_unlink(dr, NULL);
ND6_WUNLOCK();
defrouter_del(dr);
defrouter_rele(dr);
return (true);
}
/*
* for default router selection
* regards router-preference field as a 2-bit signed integer
*/
static int
rtpref(struct nd_defrouter *dr)
{
switch (dr->raflags & ND_RA_FLAG_RTPREF_MASK) {
case ND_RA_FLAG_RTPREF_HIGH:
return (RTPREF_HIGH);
case ND_RA_FLAG_RTPREF_MEDIUM:
case ND_RA_FLAG_RTPREF_RSV:
return (RTPREF_MEDIUM);
case ND_RA_FLAG_RTPREF_LOW:
return (RTPREF_LOW);
default:
/*
* This case should never happen. If it did, it would mean a
* serious bug of kernel internal. We thus always bark here.
* Or, can we even panic?
*/
log(LOG_ERR, "rtpref: impossible RA flag %x\n", dr->raflags);
return (RTPREF_INVALID);
}
/* NOTREACHED */
}
/*
* Default Router Selection according to Section 6.3.6 of RFC 2461 and
* draft-ietf-ipngwg-router-selection:
* 1) Routers that are reachable or probably reachable should be preferred.
* If we have more than one (probably) reachable router, prefer ones
* with the highest router preference.
* 2) When no routers on the list are known to be reachable or
* probably reachable, routers SHOULD be selected in a round-robin
* fashion, regardless of router preference values.
* 3) If the Default Router List is empty, assume that all
* destinations are on-link.
*
* We assume nd_defrouter is sorted by router preference value.
* Since the code below covers both with and without router preference cases,
* we do not need to classify the cases by ifdef.
*
* At this moment, we do not try to install more than one default router,
* even when the multipath routing is available, because we're not sure about
* the benefits for stub hosts comparing to the risk of making the code
* complicated and the possibility of introducing bugs.
*
* We maintain a single list of routers for multiple FIBs, only considering one
* at a time based on the receiving interface's FIB. If @fibnum is RT_ALL_FIBS,
* we do the whole thing multiple times.
*/
void
defrouter_select_fib(int fibnum)
{
struct epoch_tracker et;
struct nd_defrouter *dr, *selected_dr, *installed_dr;
struct llentry *ln = NULL;
if (fibnum == RT_ALL_FIBS) {
for (fibnum = 0; fibnum < rt_numfibs; fibnum++) {
defrouter_select_fib(fibnum);
}
}
ND6_RLOCK();
/*
* Let's handle easy case (3) first:
* If default router list is empty, there's nothing to be done.
*/
if (TAILQ_EMPTY(&V_nd6_defrouter)) {
ND6_RUNLOCK();
return;
}
/*
* Search for a (probably) reachable router from the list.
* We just pick up the first reachable one (if any), assuming that
* the ordering rule of the list described in defrtrlist_update().
*/
selected_dr = installed_dr = NULL;
TAILQ_FOREACH(dr, &V_nd6_defrouter, dr_entry) {
NET_EPOCH_ENTER(et);
if (selected_dr == NULL && dr->ifp->if_fib == fibnum &&
(ln = nd6_lookup(&dr->rtaddr, 0, dr->ifp)) &&
ND6_IS_LLINFO_PROBREACH(ln)) {
selected_dr = dr;
defrouter_ref(selected_dr);
}
NET_EPOCH_EXIT(et);
if (ln != NULL) {
LLE_RUNLOCK(ln);
ln = NULL;
}
if (dr->installed && dr->ifp->if_fib == fibnum) {
if (installed_dr == NULL) {
installed_dr = dr;
defrouter_ref(installed_dr);
} else {
/*
* this should not happen.
* warn for diagnosis.
*/
log(LOG_ERR, "defrouter_select_fib: more than "
"one router is installed\n");
}
}
}
/*
* If none of the default routers was found to be reachable,
* round-robin the list regardless of preference.
* Otherwise, if we have an installed router, check if the selected
* (reachable) router should really be preferred to the installed one.
* We only prefer the new router when the old one is not reachable
* or when the new one has a really higher preference value.
*/
if (selected_dr == NULL) {
if (installed_dr == NULL ||
TAILQ_NEXT(installed_dr, dr_entry) == NULL)
dr = TAILQ_FIRST(&V_nd6_defrouter);
else
dr = TAILQ_NEXT(installed_dr, dr_entry);
/* Ensure we select a router for this FIB. */
TAILQ_FOREACH_FROM(dr, &V_nd6_defrouter, dr_entry) {
if (dr->ifp->if_fib == fibnum) {
selected_dr = dr;
defrouter_ref(selected_dr);
break;
}
}
} else if (installed_dr != NULL) {
NET_EPOCH_ENTER(et);
if ((ln = nd6_lookup(&installed_dr->rtaddr, 0,
installed_dr->ifp)) &&
ND6_IS_LLINFO_PROBREACH(ln) &&
installed_dr->ifp->if_fib == fibnum &&
rtpref(selected_dr) <= rtpref(installed_dr)) {
defrouter_rele(selected_dr);
selected_dr = installed_dr;
}
NET_EPOCH_EXIT(et);
if (ln != NULL)
LLE_RUNLOCK(ln);
}
ND6_RUNLOCK();
NET_EPOCH_ENTER(et);
/*
* If we selected a router for this FIB and it's different
* than the installed one, remove the installed router and
* install the selected one in its place.
*/
if (installed_dr != selected_dr) {
if (installed_dr != NULL) {
defrouter_delreq(installed_dr);
defrouter_rele(installed_dr);
}
if (selected_dr != NULL)
defrouter_addreq(selected_dr);
}
if (selected_dr != NULL)
defrouter_rele(selected_dr);
NET_EPOCH_EXIT(et);
}
static struct nd_defrouter *
defrtrlist_update(struct nd_defrouter *new)
{
struct nd_defrouter *dr, *n;
uint64_t genid;
int oldpref;
bool writelocked;
if (new->rtlifetime == 0) {
defrouter_remove(&new->rtaddr, new->ifp);
return (NULL);
}
ND6_RLOCK();
writelocked = false;
restart:
dr = defrouter_lookup_locked(&new->rtaddr, new->ifp);
if (dr != NULL) {
oldpref = rtpref(dr);
/* override */
dr->raflags = new->raflags; /* XXX flag check */
dr->rtlifetime = new->rtlifetime;
dr->expire = new->expire;
/*
* If the preference does not change, there's no need
* to sort the entries. Also make sure the selected
* router is still installed in the kernel.
*/
if (dr->installed && rtpref(new) == oldpref) {
if (writelocked)
ND6_WUNLOCK();
else
ND6_RUNLOCK();
return (dr);
}
}
/*
* The router needs to be reinserted into the default router
* list, so upgrade to a write lock. If that fails and the list
* has potentially changed while the lock was dropped, we'll
* redo the lookup with the write lock held.
*/
if (!writelocked) {
writelocked = true;
if (!ND6_TRY_UPGRADE()) {
genid = V_nd6_list_genid;
ND6_RUNLOCK();
ND6_WLOCK();
if (genid != V_nd6_list_genid)
goto restart;
}
}
if (dr != NULL) {
/*
* The preferred router may have changed, so relocate this
* router.
*/
TAILQ_REMOVE(&V_nd6_defrouter, dr, dr_entry);
n = dr;
} else {
n = malloc(sizeof(*n), M_IP6NDP, M_NOWAIT | M_ZERO);
if (n == NULL) {
ND6_WUNLOCK();
return (NULL);
}
memcpy(n, new, sizeof(*n));
/* Initialize with an extra reference for the caller. */
refcount_init(&n->refcnt, 2);
}
/*
* Insert the new router in the Default Router List;
* The Default Router List should be in the descending order
* of router-preferece. Routers with the same preference are
* sorted in the arriving time order.
*/
/* insert at the end of the group */
TAILQ_FOREACH(dr, &V_nd6_defrouter, dr_entry) {
if (rtpref(n) > rtpref(dr))
break;
}
if (dr != NULL)
TAILQ_INSERT_BEFORE(dr, n, dr_entry);
else
TAILQ_INSERT_TAIL(&V_nd6_defrouter, n, dr_entry);
V_nd6_list_genid++;
ND6_WUNLOCK();
defrouter_select_fib(new->ifp->if_fib);
return (n);
}
static int
in6_init_prefix_ltimes(struct nd_prefix *ndpr)
{
if (ndpr->ndpr_pltime == ND6_INFINITE_LIFETIME)
ndpr->ndpr_preferred = 0;
else
ndpr->ndpr_preferred = time_uptime + ndpr->ndpr_pltime;
if (ndpr->ndpr_vltime == ND6_INFINITE_LIFETIME)
ndpr->ndpr_expire = 0;
else
ndpr->ndpr_expire = time_uptime + ndpr->ndpr_vltime;
return 0;
}
static void
in6_init_address_ltimes(struct nd_prefix *new, struct in6_addrlifetime *lt6)
{
/* init ia6t_expire */
if (lt6->ia6t_vltime == ND6_INFINITE_LIFETIME)
lt6->ia6t_expire = 0;
else {
lt6->ia6t_expire = time_uptime;
lt6->ia6t_expire += lt6->ia6t_vltime;
}
/* init ia6t_preferred */
if (lt6->ia6t_pltime == ND6_INFINITE_LIFETIME)
lt6->ia6t_preferred = 0;
else {
lt6->ia6t_preferred = time_uptime;
lt6->ia6t_preferred += lt6->ia6t_pltime;
}
}
static struct in6_ifaddr *
in6_ifadd(struct nd_prefixctl *pr, int mcast)
{
struct ifnet *ifp = pr->ndpr_ifp;
struct ifaddr *ifa;
struct in6_aliasreq ifra;
struct in6_ifaddr *ia, *ib;
int error, plen0;
struct in6_addr mask;
int prefixlen = pr->ndpr_plen;
int updateflags;
char ip6buf[INET6_ADDRSTRLEN];
in6_prefixlen2mask(&mask, prefixlen);
/*
* find a link-local address (will be interface ID).
* Is it really mandatory? Theoretically, a global or a site-local
* address can be configured without a link-local address, if we
* have a unique interface identifier...
*
* it is not mandatory to have a link-local address, we can generate
* interface identifier on the fly. we do this because:
* (1) it should be the easiest way to find interface identifier.
* (2) RFC2462 5.4 suggesting the use of the same interface identifier
* for multiple addresses on a single interface, and possible shortcut
* of DAD. we omitted DAD for this reason in the past.
* (3) a user can prevent autoconfiguration of global address
* by removing link-local address by hand (this is partly because we
* don't have other way to control the use of IPv6 on an interface.
* this has been our design choice - cf. NRL's "ifconfig auto").
* (4) it is easier to manage when an interface has addresses
* with the same interface identifier, than to have multiple addresses
* with different interface identifiers.
*/
ifa = (struct ifaddr *)in6ifa_ifpforlinklocal(ifp, 0); /* 0 is OK? */
if (ifa)
ib = (struct in6_ifaddr *)ifa;
else
return NULL;
/* prefixlen + ifidlen must be equal to 128 */
plen0 = in6_mask2len(&ib->ia_prefixmask.sin6_addr, NULL);
if (prefixlen != plen0) {
ifa_free(ifa);
nd6log((LOG_INFO,
"%s: wrong prefixlen for %s (prefix=%d ifid=%d)\n",
__func__, if_name(ifp), prefixlen, 128 - plen0));
return NULL;
}
/* make ifaddr */
in6_prepare_ifra(&ifra, &pr->ndpr_prefix.sin6_addr, &mask);
IN6_MASK_ADDR(&ifra.ifra_addr.sin6_addr, &mask);
/* interface ID */
ifra.ifra_addr.sin6_addr.s6_addr32[0] |=
(ib->ia_addr.sin6_addr.s6_addr32[0] & ~mask.s6_addr32[0]);
ifra.ifra_addr.sin6_addr.s6_addr32[1] |=
(ib->ia_addr.sin6_addr.s6_addr32[1] & ~mask.s6_addr32[1]);
ifra.ifra_addr.sin6_addr.s6_addr32[2] |=
(ib->ia_addr.sin6_addr.s6_addr32[2] & ~mask.s6_addr32[2]);
ifra.ifra_addr.sin6_addr.s6_addr32[3] |=
(ib->ia_addr.sin6_addr.s6_addr32[3] & ~mask.s6_addr32[3]);
ifa_free(ifa);
/* lifetimes. */
ifra.ifra_lifetime.ia6t_vltime = pr->ndpr_vltime;
ifra.ifra_lifetime.ia6t_pltime = pr->ndpr_pltime;
/* XXX: scope zone ID? */
ifra.ifra_flags |= IN6_IFF_AUTOCONF; /* obey autoconf */
/*
* Make sure that we do not have this address already. This should
* usually not happen, but we can still see this case, e.g., if we
* have manually configured the exact address to be configured.
*/
ifa = (struct ifaddr *)in6ifa_ifpwithaddr(ifp,
&ifra.ifra_addr.sin6_addr);
if (ifa != NULL) {
ifa_free(ifa);
/* this should be rare enough to make an explicit log */
log(LOG_INFO, "in6_ifadd: %s is already configured\n",
ip6_sprintf(ip6buf, &ifra.ifra_addr.sin6_addr));
return (NULL);
}
/*
* Allocate ifaddr structure, link into chain, etc.
* If we are going to create a new address upon receiving a multicasted
* RA, we need to impose a random delay before starting DAD.
* [draft-ietf-ipv6-rfc2462bis-02.txt, Section 5.4.2]
*/
updateflags = 0;
if (mcast)
updateflags |= IN6_IFAUPDATE_DADDELAY;
if ((error = in6_update_ifa(ifp, &ifra, NULL, updateflags)) != 0) {
nd6log((LOG_ERR,
"%s: failed to make ifaddr %s on %s (errno=%d)\n", __func__,
ip6_sprintf(ip6buf, &ifra.ifra_addr.sin6_addr),
if_name(ifp), error));
return (NULL); /* ifaddr must not have been allocated. */
}
ia = in6ifa_ifpwithaddr(ifp, &ifra.ifra_addr.sin6_addr);
/*
* XXXRW: Assumption of non-NULLness here might not be true with
* fine-grained locking -- should we validate it? Or just return
* earlier ifa rather than looking it up again?
*/
return (ia); /* this is always non-NULL and referenced. */
}
static struct nd_prefix *
nd6_prefix_lookup_locked(struct nd_prefixctl *key)
{
struct nd_prefix *search;
ND6_LOCK_ASSERT();
LIST_FOREACH(search, &V_nd_prefix, ndpr_entry) {
if (key->ndpr_ifp == search->ndpr_ifp &&
key->ndpr_plen == search->ndpr_plen &&
in6_are_prefix_equal(&key->ndpr_prefix.sin6_addr,
&search->ndpr_prefix.sin6_addr, key->ndpr_plen)) {
nd6_prefix_ref(search);
break;
}
}
return (search);
}
struct nd_prefix *
nd6_prefix_lookup(struct nd_prefixctl *key)
{
struct nd_prefix *search;
ND6_RLOCK();
search = nd6_prefix_lookup_locked(key);
ND6_RUNLOCK();
return (search);
}
void
nd6_prefix_ref(struct nd_prefix *pr)
{
refcount_acquire(&pr->ndpr_refcnt);
}
void
nd6_prefix_rele(struct nd_prefix *pr)
{
if (refcount_release(&pr->ndpr_refcnt)) {
KASSERT(LIST_EMPTY(&pr->ndpr_advrtrs),
("prefix %p has advertising routers", pr));
free(pr, M_IP6NDP);
}
}
int
nd6_prelist_add(struct nd_prefixctl *pr, struct nd_defrouter *dr,
struct nd_prefix **newp)
{
struct nd_prefix *new;
char ip6buf[INET6_ADDRSTRLEN];
int error;
new = malloc(sizeof(*new), M_IP6NDP, M_NOWAIT | M_ZERO);
if (new == NULL)
return (ENOMEM);
refcount_init(&new->ndpr_refcnt, newp != NULL ? 2 : 1);
new->ndpr_ifp = pr->ndpr_ifp;
new->ndpr_prefix = pr->ndpr_prefix;
new->ndpr_plen = pr->ndpr_plen;
new->ndpr_vltime = pr->ndpr_vltime;
new->ndpr_pltime = pr->ndpr_pltime;
new->ndpr_flags = pr->ndpr_flags;
if ((error = in6_init_prefix_ltimes(new)) != 0) {
free(new, M_IP6NDP);
return (error);
}
new->ndpr_lastupdate = time_uptime;
/* initialization */
LIST_INIT(&new->ndpr_advrtrs);
in6_prefixlen2mask(&new->ndpr_mask, new->ndpr_plen);
/* make prefix in the canonical form */
IN6_MASK_ADDR(&new->ndpr_prefix.sin6_addr, &new->ndpr_mask);
ND6_WLOCK();
LIST_INSERT_HEAD(&V_nd_prefix, new, ndpr_entry);
V_nd6_list_genid++;
ND6_WUNLOCK();
/* ND_OPT_PI_FLAG_ONLINK processing */
if (new->ndpr_raf_onlink) {
struct epoch_tracker et;
ND6_ONLINK_LOCK();
NET_EPOCH_ENTER(et);
if ((error = nd6_prefix_onlink(new)) != 0) {
nd6log((LOG_ERR, "%s: failed to make the prefix %s/%d "
"on-link on %s (errno=%d)\n", __func__,
ip6_sprintf(ip6buf, &pr->ndpr_prefix.sin6_addr),
pr->ndpr_plen, if_name(pr->ndpr_ifp), error));
/* proceed anyway. XXX: is it correct? */
}
NET_EPOCH_EXIT(et);
ND6_ONLINK_UNLOCK();
}
if (dr != NULL)
pfxrtr_add(new, dr);
if (newp != NULL)
*newp = new;
return (0);
}
/*
* Remove a prefix from the prefix list and optionally stash it in a
* caller-provided list.
*
* The ND6 lock must be held.
*/
void
nd6_prefix_unlink(struct nd_prefix *pr, struct nd_prhead *list)
{
ND6_WLOCK_ASSERT();
LIST_REMOVE(pr, ndpr_entry);
V_nd6_list_genid++;
if (list != NULL)
LIST_INSERT_HEAD(list, pr, ndpr_entry);
}
/*
* Free an unlinked prefix, first marking it off-link if necessary.
*/
void
nd6_prefix_del(struct nd_prefix *pr)
{
struct nd_pfxrouter *pfr, *next;
int e;
char ip6buf[INET6_ADDRSTRLEN];
KASSERT(pr->ndpr_addrcnt == 0,
("prefix %p has referencing addresses", pr));
ND6_UNLOCK_ASSERT();
/*
* Though these flags are now meaningless, we'd rather keep the value
* of pr->ndpr_raf_onlink and pr->ndpr_raf_auto not to confuse users
* when executing "ndp -p".
*/
if ((pr->ndpr_stateflags & NDPRF_ONLINK) != 0) {
ND6_ONLINK_LOCK();
if ((e = nd6_prefix_offlink(pr)) != 0) {
nd6log((LOG_ERR,
"%s: failed to make the prefix %s/%d offlink on %s "
"(errno=%d)\n", __func__,
ip6_sprintf(ip6buf, &pr->ndpr_prefix.sin6_addr),
pr->ndpr_plen, if_name(pr->ndpr_ifp), e));
/* what should we do? */
}
ND6_ONLINK_UNLOCK();
}
/* Release references to routers that have advertised this prefix. */
ND6_WLOCK();
LIST_FOREACH_SAFE(pfr, &pr->ndpr_advrtrs, pfr_entry, next)
pfxrtr_del(pfr);
ND6_WUNLOCK();
nd6_prefix_rele(pr);
pfxlist_onlink_check();
}
static int
prelist_update(struct nd_prefixctl *new, struct nd_defrouter *dr,
struct mbuf *m, int mcast)
{
struct in6_ifaddr *ia6 = NULL, *ia6_match = NULL;
struct ifaddr *ifa;
struct ifnet *ifp = new->ndpr_ifp;
struct nd_prefix *pr;
int error = 0;
int auth;
struct in6_addrlifetime lt6_tmp;
char ip6buf[INET6_ADDRSTRLEN];
NET_EPOCH_ASSERT();
auth = 0;
if (m) {
/*
* Authenticity for NA consists authentication for
* both IP header and IP datagrams, doesn't it ?
*/
#if defined(M_AUTHIPHDR) && defined(M_AUTHIPDGM)
auth = ((m->m_flags & M_AUTHIPHDR) &&
(m->m_flags & M_AUTHIPDGM));
#endif
}
if ((pr = nd6_prefix_lookup(new)) != NULL) {
/*
* nd6_prefix_lookup() ensures that pr and new have the same
* prefix on a same interface.
*/
/*
* Update prefix information. Note that the on-link (L) bit
* and the autonomous (A) bit should NOT be changed from 1
* to 0.
*/
if (new->ndpr_raf_onlink == 1)
pr->ndpr_raf_onlink = 1;
if (new->ndpr_raf_auto == 1)
pr->ndpr_raf_auto = 1;
if (new->ndpr_raf_onlink) {
pr->ndpr_vltime = new->ndpr_vltime;
pr->ndpr_pltime = new->ndpr_pltime;
(void)in6_init_prefix_ltimes(pr); /* XXX error case? */
pr->ndpr_lastupdate = time_uptime;
}
if (new->ndpr_raf_onlink &&
(pr->ndpr_stateflags & NDPRF_ONLINK) == 0) {
ND6_ONLINK_LOCK();
if ((error = nd6_prefix_onlink(pr)) != 0) {
nd6log((LOG_ERR,
"%s: failed to make the prefix %s/%d "
"on-link on %s (errno=%d)\n", __func__,
ip6_sprintf(ip6buf,
&pr->ndpr_prefix.sin6_addr),
pr->ndpr_plen, if_name(pr->ndpr_ifp),
error));
/* proceed anyway. XXX: is it correct? */
}
ND6_ONLINK_UNLOCK();
}
if (dr != NULL)
pfxrtr_add(pr, dr);
} else {
if (new->ndpr_vltime == 0)
goto end;
if (new->ndpr_raf_onlink == 0 && new->ndpr_raf_auto == 0)
goto end;
error = nd6_prelist_add(new, dr, &pr);
if (error != 0) {
nd6log((LOG_NOTICE, "%s: nd6_prelist_add() failed for "
"the prefix %s/%d on %s (errno=%d)\n", __func__,
ip6_sprintf(ip6buf, &new->ndpr_prefix.sin6_addr),
new->ndpr_plen, if_name(new->ndpr_ifp), error));
goto end; /* we should just give up in this case. */
}
/*
* XXX: from the ND point of view, we can ignore a prefix
* with the on-link bit being zero. However, we need a
* prefix structure for references from autoconfigured
* addresses. Thus, we explicitly make sure that the prefix
* itself expires now.
*/
if (pr->ndpr_raf_onlink == 0) {
pr->ndpr_vltime = 0;
pr->ndpr_pltime = 0;
in6_init_prefix_ltimes(pr);
}
}
/*
* Address autoconfiguration based on Section 5.5.3 of RFC 2462.
* Note that pr must be non NULL at this point.
*/
/* 5.5.3 (a). Ignore the prefix without the A bit set. */
if (!new->ndpr_raf_auto)
goto end;
/*
* 5.5.3 (b). the link-local prefix should have been ignored in
* nd6_ra_input.
*/
/* 5.5.3 (c). Consistency check on lifetimes: pltime <= vltime. */
if (new->ndpr_pltime > new->ndpr_vltime) {
error = EINVAL; /* XXX: won't be used */
goto end;
}
/*
* 5.5.3 (d). If the prefix advertised is not equal to the prefix of
* an address configured by stateless autoconfiguration already in the
* list of addresses associated with the interface, and the Valid
* Lifetime is not 0, form an address. We first check if we have
* a matching prefix.
* Note: we apply a clarification in rfc2462bis-02 here. We only
* consider autoconfigured addresses while RFC2462 simply said
* "address".
*/
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
struct in6_ifaddr *ifa6;
u_int32_t remaininglifetime;
if (ifa->ifa_addr->sa_family != AF_INET6)
continue;
ifa6 = (struct in6_ifaddr *)ifa;
/*
* We only consider autoconfigured addresses as per rfc2462bis.
*/
if (!(ifa6->ia6_flags & IN6_IFF_AUTOCONF))
continue;
/*
* Spec is not clear here, but I believe we should concentrate
* on unicast (i.e. not anycast) addresses.
* XXX: other ia6_flags? detached or duplicated?
*/
if ((ifa6->ia6_flags & IN6_IFF_ANYCAST) != 0)
continue;
/*
* Ignore the address if it is not associated with a prefix
* or is associated with a prefix that is different from this
* one. (pr is never NULL here)
*/
if (ifa6->ia6_ndpr != pr)
continue;
if (ia6_match == NULL) /* remember the first one */
ia6_match = ifa6;
/*
* An already autoconfigured address matched. Now that we
* are sure there is at least one matched address, we can
* proceed to 5.5.3. (e): update the lifetimes according to the
* "two hours" rule and the privacy extension.
* We apply some clarifications in rfc2462bis:
* - use remaininglifetime instead of storedlifetime as a
* variable name
* - remove the dead code in the "two-hour" rule
*/
#define TWOHOUR (120*60)
lt6_tmp = ifa6->ia6_lifetime;
if (lt6_tmp.ia6t_vltime == ND6_INFINITE_LIFETIME)
remaininglifetime = ND6_INFINITE_LIFETIME;
else if (time_uptime - ifa6->ia6_updatetime >
lt6_tmp.ia6t_vltime) {
/*
* The case of "invalid" address. We should usually
* not see this case.
*/
remaininglifetime = 0;
} else
remaininglifetime = lt6_tmp.ia6t_vltime -
(time_uptime - ifa6->ia6_updatetime);
/* when not updating, keep the current stored lifetime. */
lt6_tmp.ia6t_vltime = remaininglifetime;
if (TWOHOUR < new->ndpr_vltime ||
remaininglifetime < new->ndpr_vltime) {
lt6_tmp.ia6t_vltime = new->ndpr_vltime;
} else if (remaininglifetime <= TWOHOUR) {
if (auth) {
lt6_tmp.ia6t_vltime = new->ndpr_vltime;
}
} else {
/*
* new->ndpr_vltime <= TWOHOUR &&
* TWOHOUR < remaininglifetime
*/
lt6_tmp.ia6t_vltime = TWOHOUR;
}
/* The 2 hour rule is not imposed for preferred lifetime. */
lt6_tmp.ia6t_pltime = new->ndpr_pltime;
in6_init_address_ltimes(pr, <6_tmp);
/*
* We need to treat lifetimes for temporary addresses
* differently, according to
* draft-ietf-ipv6-privacy-addrs-v2-01.txt 3.3 (1);
* we only update the lifetimes when they are in the maximum
* intervals.
*/
if ((ifa6->ia6_flags & IN6_IFF_TEMPORARY) != 0) {
u_int32_t maxvltime, maxpltime;
if (V_ip6_temp_valid_lifetime >
(u_int32_t)((time_uptime - ifa6->ia6_createtime) +
V_ip6_desync_factor)) {
maxvltime = V_ip6_temp_valid_lifetime -
(time_uptime - ifa6->ia6_createtime) -
V_ip6_desync_factor;
} else
maxvltime = 0;
if (V_ip6_temp_preferred_lifetime >
(u_int32_t)((time_uptime - ifa6->ia6_createtime) +
V_ip6_desync_factor)) {
maxpltime = V_ip6_temp_preferred_lifetime -
(time_uptime - ifa6->ia6_createtime) -
V_ip6_desync_factor;
} else
maxpltime = 0;
if (lt6_tmp.ia6t_vltime == ND6_INFINITE_LIFETIME ||
lt6_tmp.ia6t_vltime > maxvltime) {
lt6_tmp.ia6t_vltime = maxvltime;
}
if (lt6_tmp.ia6t_pltime == ND6_INFINITE_LIFETIME ||
lt6_tmp.ia6t_pltime > maxpltime) {
lt6_tmp.ia6t_pltime = maxpltime;
}
}
ifa6->ia6_lifetime = lt6_tmp;
ifa6->ia6_updatetime = time_uptime;
}
if (ia6_match == NULL && new->ndpr_vltime) {
int ifidlen;
/*
* 5.5.3 (d) (continued)
* No address matched and the valid lifetime is non-zero.
* Create a new address.
*/
/*
* Prefix Length check:
* If the sum of the prefix length and interface identifier
* length does not equal 128 bits, the Prefix Information
* option MUST be ignored. The length of the interface
* identifier is defined in a separate link-type specific
* document.
*/
ifidlen = in6_if2idlen(ifp);
if (ifidlen < 0) {
/* this should not happen, so we always log it. */
log(LOG_ERR, "prelist_update: IFID undefined (%s)\n",
if_name(ifp));
goto end;
}
if (ifidlen + pr->ndpr_plen != 128) {
nd6log((LOG_INFO,
"%s: invalid prefixlen %d for %s, ignored\n",
__func__, pr->ndpr_plen, if_name(ifp)));
goto end;
}
if ((ia6 = in6_ifadd(new, mcast)) != NULL) {
/*
* note that we should use pr (not new) for reference.
*/
pr->ndpr_addrcnt++;
ia6->ia6_ndpr = pr;
/*
* RFC 3041 3.3 (2).
* When a new public address is created as described
* in RFC2462, also create a new temporary address.
*
* RFC 3041 3.5.
* When an interface connects to a new link, a new
* randomized interface identifier should be generated
* immediately together with a new set of temporary
* addresses. Thus, we specifiy 1 as the 2nd arg of
* in6_tmpifadd().
*/
if (V_ip6_use_tempaddr) {
int e;
if ((e = in6_tmpifadd(ia6, 1, 1)) != 0) {
nd6log((LOG_NOTICE, "%s: failed to "
"create a temporary address "
"(errno=%d)\n", __func__, e));
}
}
ifa_free(&ia6->ia_ifa);
/*
* A newly added address might affect the status
* of other addresses, so we check and update it.
* XXX: what if address duplication happens?
*/
pfxlist_onlink_check();
} else {
/* just set an error. do not bark here. */
error = EADDRNOTAVAIL; /* XXX: might be unused. */
}
}
end:
if (pr != NULL)
nd6_prefix_rele(pr);
return (error);
}
/*
* A supplement function used in the on-link detection below;
* detect if a given prefix has a (probably) reachable advertising router.
* XXX: lengthy function name...
*/
static struct nd_pfxrouter *
find_pfxlist_reachable_router(struct nd_prefix *pr)
{
struct epoch_tracker et;
struct nd_pfxrouter *pfxrtr;
struct llentry *ln;
int canreach;
ND6_LOCK_ASSERT();
NET_EPOCH_ENTER(et);
LIST_FOREACH(pfxrtr, &pr->ndpr_advrtrs, pfr_entry) {
ln = nd6_lookup(&pfxrtr->router->rtaddr, 0, pfxrtr->router->ifp);
if (ln == NULL)
continue;
canreach = ND6_IS_LLINFO_PROBREACH(ln);
LLE_RUNLOCK(ln);
if (canreach)
break;
}
NET_EPOCH_EXIT(et);
return (pfxrtr);
}
/*
* Check if each prefix in the prefix list has at least one available router
* that advertised the prefix (a router is "available" if its neighbor cache
* entry is reachable or probably reachable).
* If the check fails, the prefix may be off-link, because, for example,
* we have moved from the network but the lifetime of the prefix has not
* expired yet. So we should not use the prefix if there is another prefix
* that has an available router.
* But, if there is no prefix that has an available router, we still regard
* all the prefixes as on-link. This is because we can't tell if all the
* routers are simply dead or if we really moved from the network and there
* is no router around us.
*/
void
pfxlist_onlink_check(void)
{
struct nd_prefix *pr;
struct in6_ifaddr *ifa;
struct nd_defrouter *dr;
struct nd_pfxrouter *pfxrtr = NULL;
struct rm_priotracker in6_ifa_tracker;
uint64_t genid;
uint32_t flags;
ND6_ONLINK_LOCK();
ND6_RLOCK();
/*
* Check if there is a prefix that has a reachable advertising
* router.
*/
LIST_FOREACH(pr, &V_nd_prefix, ndpr_entry) {
if (pr->ndpr_raf_onlink && find_pfxlist_reachable_router(pr))
break;
}
/*
* If we have no such prefix, check whether we still have a router
* that does not advertise any prefixes.
*/
if (pr == NULL) {
TAILQ_FOREACH(dr, &V_nd6_defrouter, dr_entry) {
struct nd_prefix *pr0;
LIST_FOREACH(pr0, &V_nd_prefix, ndpr_entry) {
if ((pfxrtr = pfxrtr_lookup(pr0, dr)) != NULL)
break;
}
if (pfxrtr != NULL)
break;
}
}
if (pr != NULL || (!TAILQ_EMPTY(&V_nd6_defrouter) && pfxrtr == NULL)) {
/*
* There is at least one prefix that has a reachable router,
* or at least a router which probably does not advertise
* any prefixes. The latter would be the case when we move
* to a new link where we have a router that does not provide
* prefixes and we configure an address by hand.
* Detach prefixes which have no reachable advertising
* router, and attach other prefixes.
*/
LIST_FOREACH(pr, &V_nd_prefix, ndpr_entry) {
/* XXX: a link-local prefix should never be detached */
if (IN6_IS_ADDR_LINKLOCAL(&pr->ndpr_prefix.sin6_addr) ||
pr->ndpr_raf_onlink == 0 ||
pr->ndpr_raf_auto == 0)
continue;
if ((pr->ndpr_stateflags & NDPRF_DETACHED) == 0 &&
find_pfxlist_reachable_router(pr) == NULL)
pr->ndpr_stateflags |= NDPRF_DETACHED;
else if ((pr->ndpr_stateflags & NDPRF_DETACHED) != 0 &&
find_pfxlist_reachable_router(pr) != NULL)
pr->ndpr_stateflags &= ~NDPRF_DETACHED;
}
} else {
/* there is no prefix that has a reachable router */
LIST_FOREACH(pr, &V_nd_prefix, ndpr_entry) {
if (IN6_IS_ADDR_LINKLOCAL(&pr->ndpr_prefix.sin6_addr) ||
pr->ndpr_raf_onlink == 0 ||
pr->ndpr_raf_auto == 0)
continue;
pr->ndpr_stateflags &= ~NDPRF_DETACHED;
}
}
/*
* Remove each interface route associated with a (just) detached
* prefix, and reinstall the interface route for a (just) attached
* prefix. Note that all attempt of reinstallation does not
* necessarily success, when a same prefix is shared among multiple
* interfaces. Such cases will be handled in nd6_prefix_onlink,
* so we don't have to care about them.
*/
restart:
LIST_FOREACH(pr, &V_nd_prefix, ndpr_entry) {
char ip6buf[INET6_ADDRSTRLEN];
int e;
if (IN6_IS_ADDR_LINKLOCAL(&pr->ndpr_prefix.sin6_addr) ||
pr->ndpr_raf_onlink == 0 ||
pr->ndpr_raf_auto == 0)
continue;
flags = pr->ndpr_stateflags & (NDPRF_DETACHED | NDPRF_ONLINK);
if (flags == 0 || flags == (NDPRF_DETACHED | NDPRF_ONLINK)) {
genid = V_nd6_list_genid;
ND6_RUNLOCK();
if ((flags & NDPRF_ONLINK) != 0 &&
(e = nd6_prefix_offlink(pr)) != 0) {
nd6log((LOG_ERR,
"%s: failed to make %s/%d offlink "
"(errno=%d)\n", __func__,
ip6_sprintf(ip6buf,
&pr->ndpr_prefix.sin6_addr),
pr->ndpr_plen, e));
} else if ((flags & NDPRF_ONLINK) == 0 &&
(e = nd6_prefix_onlink(pr)) != 0) {
nd6log((LOG_ERR,
"%s: failed to make %s/%d onlink "
"(errno=%d)\n", __func__,
ip6_sprintf(ip6buf,
&pr->ndpr_prefix.sin6_addr),
pr->ndpr_plen, e));
}
ND6_RLOCK();
if (genid != V_nd6_list_genid)
goto restart;
}
}
/*
* Changes on the prefix status might affect address status as well.
* Make sure that all addresses derived from an attached prefix are
* attached, and that all addresses derived from a detached prefix are
* detached. Note, however, that a manually configured address should
* always be attached.
* The precise detection logic is same as the one for prefixes.
*/
IN6_IFADDR_RLOCK(&in6_ifa_tracker);
CK_STAILQ_FOREACH(ifa, &V_in6_ifaddrhead, ia_link) {
if (!(ifa->ia6_flags & IN6_IFF_AUTOCONF))
continue;
if (ifa->ia6_ndpr == NULL) {
/*
* This can happen when we first configure the address
* (i.e. the address exists, but the prefix does not).
* XXX: complicated relationships...
*/
continue;
}
if (find_pfxlist_reachable_router(ifa->ia6_ndpr))
break;
}
if (ifa) {
CK_STAILQ_FOREACH(ifa, &V_in6_ifaddrhead, ia_link) {
if ((ifa->ia6_flags & IN6_IFF_AUTOCONF) == 0)
continue;
if (ifa->ia6_ndpr == NULL) /* XXX: see above. */
continue;
if (find_pfxlist_reachable_router(ifa->ia6_ndpr)) {
if (ifa->ia6_flags & IN6_IFF_DETACHED) {
ifa->ia6_flags &= ~IN6_IFF_DETACHED;
ifa->ia6_flags |= IN6_IFF_TENTATIVE;
nd6_dad_start((struct ifaddr *)ifa, 0);
}
} else {
ifa->ia6_flags |= IN6_IFF_DETACHED;
}
}
} else {
CK_STAILQ_FOREACH(ifa, &V_in6_ifaddrhead, ia_link) {
if ((ifa->ia6_flags & IN6_IFF_AUTOCONF) == 0)
continue;
if (ifa->ia6_flags & IN6_IFF_DETACHED) {
ifa->ia6_flags &= ~IN6_IFF_DETACHED;
ifa->ia6_flags |= IN6_IFF_TENTATIVE;
/* Do we need a delay in this case? */
nd6_dad_start((struct ifaddr *)ifa, 0);
}
}
}
IN6_IFADDR_RUNLOCK(&in6_ifa_tracker);
ND6_RUNLOCK();
ND6_ONLINK_UNLOCK();
}
+/*
+ * Add or remove interface route specified by @dst, @netmask and @ifp.
+ * ifa can be NULL.
+ * Returns 0 on success
+ */
+static int
+nd6_prefix_rtrequest(uint32_t fibnum, int cmd, struct sockaddr_in6 *dst,
+ struct sockaddr_in6 *netmask, struct ifnet *ifp, struct ifaddr *ifa)
+{
+ struct epoch_tracker et;
+ int error;
+
+ /* Prepare gateway */
+ struct sockaddr_dl_short sdl = {
+ .sdl_family = AF_LINK,
+ .sdl_len = sizeof(struct sockaddr_dl_short),
+ .sdl_type = ifp->if_type,
+ .sdl_index = ifp->if_index,
+ };
+
+ struct rt_addrinfo info = {
+ .rti_ifa = ifa,
+ .rti_flags = RTF_PINNED | ((netmask != NULL) ? 0 : RTF_HOST),
+ .rti_info = {
+ [RTAX_DST] = (struct sockaddr *)dst,
+ [RTAX_NETMASK] = (struct sockaddr *)netmask,
+ [RTAX_GATEWAY] = (struct sockaddr *)&sdl,
+ },
+ };
+ /* Don't set additional per-gw filters on removal */
+
+ NET_EPOCH_ENTER(et);
+ error = rib_handle_ifaddr_info(fibnum, cmd, &info);
+ NET_EPOCH_EXIT(et);
+ return (error);
+}
+
static int
nd6_prefix_onlink_rtrequest(struct nd_prefix *pr, struct ifaddr *ifa)
{
- struct sockaddr_dl_short sdl;
- struct sockaddr_in6 mask6;
- u_long rtflags;
- int error, a_failure, fibnum, maxfib;
-
- bzero(&mask6, sizeof(mask6));
- mask6.sin6_len = sizeof(mask6);
- mask6.sin6_addr = pr->ndpr_mask;
- rtflags = (ifa->ifa_flags & ~IFA_RTSELF) | RTF_UP;
-
- bzero(&sdl, sizeof(struct sockaddr_dl_short));
- sdl.sdl_len = sizeof(struct sockaddr_dl_short);
- sdl.sdl_family = AF_LINK;
- sdl.sdl_type = ifa->ifa_ifp->if_type;
- sdl.sdl_index = ifa->ifa_ifp->if_index;
-
- if(V_rt_add_addr_allfibs) {
- fibnum = 0;
- maxfib = rt_numfibs;
- } else {
- fibnum = ifa->ifa_ifp->if_fib;
- maxfib = fibnum + 1;
- }
- a_failure = 0;
- for (; fibnum < maxfib; fibnum++) {
- struct rt_addrinfo info;
- struct rib_cmd_info rc;
-
- bzero((caddr_t)&info, sizeof(info));
- info.rti_flags = rtflags;
- info.rti_info[RTAX_DST] = (struct sockaddr *)&pr->ndpr_prefix;
- info.rti_info[RTAX_GATEWAY] = (struct sockaddr *)&sdl;
- info.rti_info[RTAX_NETMASK] = (struct sockaddr *)&mask6;
-
- NET_EPOCH_ASSERT();
- error = rib_action(fibnum, RTM_ADD, &info, &rc);
- if (error != 0) {
- char ip6buf[INET6_ADDRSTRLEN];
- char ip6bufg[INET6_ADDRSTRLEN];
- char ip6bufm[INET6_ADDRSTRLEN];
- struct sockaddr_in6 *sin6;
-
- sin6 = (struct sockaddr_in6 *)ifa->ifa_addr;
- nd6log((LOG_ERR, "%s: failed to add "
- "route for a prefix (%s/%d) on %s, gw=%s, mask=%s, "
- "flags=%lx errno = %d\n", __func__,
- ip6_sprintf(ip6buf, &pr->ndpr_prefix.sin6_addr),
- pr->ndpr_plen, if_name(pr->ndpr_ifp),
- ip6_sprintf(ip6bufg, &sin6->sin6_addr),
- ip6_sprintf(ip6bufm, &mask6.sin6_addr),
- rtflags, error));
+ int error;
- /* Save last error to return, see rtinit(). */
- a_failure = error;
- continue;
- }
+ struct sockaddr_in6 mask6 = {
+ .sin6_family = AF_INET6,
+ .sin6_len = sizeof(struct sockaddr_in6),
+ .sin6_addr = pr->ndpr_mask,
+ };
+ struct sockaddr_in6 *pmask6 = (pr->ndpr_plen != 128) ? &mask6 : NULL;
+ error = nd6_prefix_rtrequest(pr->ndpr_ifp->if_fib, RTM_ADD,
+ &pr->ndpr_prefix, pmask6, pr->ndpr_ifp, ifa);
+ if (error == 0)
pr->ndpr_stateflags |= NDPRF_ONLINK;
- struct nhop_object *nh = nhop_select(rc.rc_nh_new, 0);
- rt_routemsg(RTM_ADD, rc.rc_rt, nh, fibnum);
- }
- /* Return the last error we got. */
- return (a_failure);
+ return (error);
}
static int
nd6_prefix_onlink(struct nd_prefix *pr)
{
struct epoch_tracker et;
struct ifaddr *ifa;
struct ifnet *ifp = pr->ndpr_ifp;
struct nd_prefix *opr;
char ip6buf[INET6_ADDRSTRLEN];
int error;
ND6_ONLINK_LOCK_ASSERT();
ND6_UNLOCK_ASSERT();
if ((pr->ndpr_stateflags & NDPRF_ONLINK) != 0)
return (EEXIST);
/*
* Add the interface route associated with the prefix. Before
* installing the route, check if there's the same prefix on another
* interface, and the prefix has already installed the interface route.
* Although such a configuration is expected to be rare, we explicitly
* allow it.
*/
ND6_RLOCK();
LIST_FOREACH(opr, &V_nd_prefix, ndpr_entry) {
if (opr == pr)
continue;
if ((opr->ndpr_stateflags & NDPRF_ONLINK) == 0)
continue;
if (!V_rt_add_addr_allfibs &&
opr->ndpr_ifp->if_fib != pr->ndpr_ifp->if_fib)
continue;
if (opr->ndpr_plen == pr->ndpr_plen &&
in6_are_prefix_equal(&pr->ndpr_prefix.sin6_addr,
&opr->ndpr_prefix.sin6_addr, pr->ndpr_plen)) {
ND6_RUNLOCK();
return (0);
}
}
ND6_RUNLOCK();
/*
* We prefer link-local addresses as the associated interface address.
*/
/* search for a link-local addr */
NET_EPOCH_ENTER(et);
ifa = (struct ifaddr *)in6ifa_ifpforlinklocal(ifp,
IN6_IFF_NOTREADY | IN6_IFF_ANYCAST);
if (ifa == NULL) {
/* XXX: freebsd does not have ifa_ifwithaf */
CK_STAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
if (ifa->ifa_addr->sa_family == AF_INET6) {
ifa_ref(ifa);
break;
}
}
/* should we care about ia6_flags? */
}
if (ifa == NULL) {
/*
* This can still happen, when, for example, we receive an RA
* containing a prefix with the L bit set and the A bit clear,
* after removing all IPv6 addresses on the receiving
* interface. This should, of course, be rare though.
*/
nd6log((LOG_NOTICE,
"%s: failed to find any ifaddr to add route for a "
"prefix(%s/%d) on %s\n", __func__,
ip6_sprintf(ip6buf, &pr->ndpr_prefix.sin6_addr),
pr->ndpr_plen, if_name(ifp)));
error = 0;
} else {
error = nd6_prefix_onlink_rtrequest(pr, ifa);
ifa_free(ifa);
}
NET_EPOCH_EXIT(et);
return (error);
}
int
nd6_prefix_offlink(struct nd_prefix *pr)
{
int error = 0;
struct ifnet *ifp = pr->ndpr_ifp;
struct nd_prefix *opr;
- struct sockaddr_in6 sa6, mask6;
+ struct sockaddr_in6 sa6;
char ip6buf[INET6_ADDRSTRLEN];
uint64_t genid;
- int fibnum, maxfib, a_failure;
- struct epoch_tracker et;
+ int a_failure;
ND6_ONLINK_LOCK_ASSERT();
ND6_UNLOCK_ASSERT();
if ((pr->ndpr_stateflags & NDPRF_ONLINK) == 0)
return (EEXIST);
- bzero(&sa6, sizeof(sa6));
- sa6.sin6_family = AF_INET6;
- sa6.sin6_len = sizeof(sa6);
- bcopy(&pr->ndpr_prefix.sin6_addr, &sa6.sin6_addr,
- sizeof(struct in6_addr));
- bzero(&mask6, sizeof(mask6));
- mask6.sin6_family = AF_INET6;
- mask6.sin6_len = sizeof(sa6);
- bcopy(&pr->ndpr_mask, &mask6.sin6_addr, sizeof(struct in6_addr));
-
- if (V_rt_add_addr_allfibs) {
- fibnum = 0;
- maxfib = rt_numfibs;
- } else {
- fibnum = ifp->if_fib;
- maxfib = fibnum + 1;
- }
+ struct sockaddr_in6 mask6 = {
+ .sin6_family = AF_INET6,
+ .sin6_len = sizeof(struct sockaddr_in6),
+ .sin6_addr = pr->ndpr_mask,
+ };
+ struct sockaddr_in6 *pmask6 = (pr->ndpr_plen != 128) ? &mask6 : NULL;
- a_failure = 0;
- NET_EPOCH_ENTER(et);
- for (; fibnum < maxfib; fibnum++) {
- struct rt_addrinfo info;
- struct rib_cmd_info rc;
-
- bzero((caddr_t)&info, sizeof(info));
- info.rti_flags = RTF_GATEWAY;
- info.rti_info[RTAX_DST] = (struct sockaddr *)&sa6;
- info.rti_info[RTAX_GATEWAY] = NULL;
- info.rti_info[RTAX_NETMASK] = (struct sockaddr *)&mask6;
-
- NET_EPOCH_ASSERT();
- error = rib_action(fibnum, RTM_DELETE, &info, &rc);
- if (error != 0) {
- /* Save last error to return, see rtinit(). */
- a_failure = error;
- continue;
- }
+ error = nd6_prefix_rtrequest(ifp->if_fib, RTM_DELETE,
+ &pr->ndpr_prefix, pmask6, ifp, NULL);
- /* report route deletion to the routing socket. */
- struct nhop_object *nh = nhop_select(rc.rc_nh_old, 0);
- rt_routemsg(RTM_DELETE, rc.rc_rt, nh, fibnum);
- }
- NET_EPOCH_EXIT(et);
- error = a_failure;
a_failure = 1;
if (error == 0) {
pr->ndpr_stateflags &= ~NDPRF_ONLINK;
/*
* There might be the same prefix on another interface,
* the prefix which could not be on-link just because we have
* the interface route (see comments in nd6_prefix_onlink).
* If there's one, try to make the prefix on-link on the
* interface.
*/
ND6_RLOCK();
restart:
LIST_FOREACH(opr, &V_nd_prefix, ndpr_entry) {
/*
* KAME specific: detached prefixes should not be
* on-link.
*/
if (opr == pr || (opr->ndpr_stateflags &
(NDPRF_ONLINK | NDPRF_DETACHED)) != 0)
continue;
if (opr->ndpr_plen == pr->ndpr_plen &&
in6_are_prefix_equal(&pr->ndpr_prefix.sin6_addr,
&opr->ndpr_prefix.sin6_addr, pr->ndpr_plen)) {
int e;
genid = V_nd6_list_genid;
ND6_RUNLOCK();
if ((e = nd6_prefix_onlink(opr)) != 0) {
nd6log((LOG_ERR,
"%s: failed to recover a prefix "
"%s/%d from %s to %s (errno=%d)\n",
__func__, ip6_sprintf(ip6buf,
&opr->ndpr_prefix.sin6_addr),
opr->ndpr_plen, if_name(ifp),
if_name(opr->ndpr_ifp), e));
} else
a_failure = 0;
ND6_RLOCK();
if (genid != V_nd6_list_genid)
goto restart;
}
}
ND6_RUNLOCK();
} else {
/* XXX: can we still set the NDPRF_ONLINK flag? */
nd6log((LOG_ERR,
"%s: failed to delete route: %s/%d on %s (errno=%d)\n",
- __func__, ip6_sprintf(ip6buf, &sa6.sin6_addr),
+ __func__, ip6_sprintf(ip6buf, &pr->ndpr_prefix.sin6_addr),
pr->ndpr_plen, if_name(ifp), error));
}
if (a_failure)
lltable_prefix_free(AF_INET6, (struct sockaddr *)&sa6,
(struct sockaddr *)&mask6, LLE_STATIC);
return (error);
}
/*
* ia0 - corresponding public address
*/
int
in6_tmpifadd(const struct in6_ifaddr *ia0, int forcegen, int delay)
{
struct ifnet *ifp = ia0->ia_ifa.ifa_ifp;
struct in6_ifaddr *newia;
struct in6_aliasreq ifra;
int error;
int trylimit = 3; /* XXX: adhoc value */
int updateflags;
u_int32_t randid[2];
time_t vltime0, pltime0;
in6_prepare_ifra(&ifra, &ia0->ia_addr.sin6_addr,
&ia0->ia_prefixmask.sin6_addr);
ifra.ifra_addr = ia0->ia_addr; /* XXX: do we need this ? */
/* clear the old IFID */
IN6_MASK_ADDR(&ifra.ifra_addr.sin6_addr,
&ifra.ifra_prefixmask.sin6_addr);
again:
if (in6_get_tmpifid(ifp, (u_int8_t *)randid,
(const u_int8_t *)&ia0->ia_addr.sin6_addr.s6_addr[8], forcegen)) {
nd6log((LOG_NOTICE, "%s: failed to find a good random IFID\n",
__func__));
return (EINVAL);
}
ifra.ifra_addr.sin6_addr.s6_addr32[2] |=
(randid[0] & ~(ifra.ifra_prefixmask.sin6_addr.s6_addr32[2]));
ifra.ifra_addr.sin6_addr.s6_addr32[3] |=
(randid[1] & ~(ifra.ifra_prefixmask.sin6_addr.s6_addr32[3]));
/*
* in6_get_tmpifid() quite likely provided a unique interface ID.
* However, we may still have a chance to see collision, because
* there may be a time lag between generation of the ID and generation
* of the address. So, we'll do one more sanity check.
*/
if (in6_localip(&ifra.ifra_addr.sin6_addr) != 0) {
if (trylimit-- > 0) {
forcegen = 1;
goto again;
}
/* Give up. Something strange should have happened. */
nd6log((LOG_NOTICE, "%s: failed to find a unique random IFID\n",
__func__));
return (EEXIST);
}
/*
* The Valid Lifetime is the lower of the Valid Lifetime of the
* public address or TEMP_VALID_LIFETIME.
* The Preferred Lifetime is the lower of the Preferred Lifetime
* of the public address or TEMP_PREFERRED_LIFETIME -
* DESYNC_FACTOR.
*/
if (ia0->ia6_lifetime.ia6t_vltime != ND6_INFINITE_LIFETIME) {
vltime0 = IFA6_IS_INVALID(ia0) ? 0 :
(ia0->ia6_lifetime.ia6t_vltime -
(time_uptime - ia0->ia6_updatetime));
if (vltime0 > V_ip6_temp_valid_lifetime)
vltime0 = V_ip6_temp_valid_lifetime;
} else
vltime0 = V_ip6_temp_valid_lifetime;
if (ia0->ia6_lifetime.ia6t_pltime != ND6_INFINITE_LIFETIME) {
pltime0 = IFA6_IS_DEPRECATED(ia0) ? 0 :
(ia0->ia6_lifetime.ia6t_pltime -
(time_uptime - ia0->ia6_updatetime));
if (pltime0 > V_ip6_temp_preferred_lifetime - V_ip6_desync_factor){
pltime0 = V_ip6_temp_preferred_lifetime -
V_ip6_desync_factor;
}
} else
pltime0 = V_ip6_temp_preferred_lifetime - V_ip6_desync_factor;
ifra.ifra_lifetime.ia6t_vltime = vltime0;
ifra.ifra_lifetime.ia6t_pltime = pltime0;
/*
* A temporary address is created only if this calculated Preferred
* Lifetime is greater than REGEN_ADVANCE time units.
*/
if (ifra.ifra_lifetime.ia6t_pltime <= V_ip6_temp_regen_advance)
return (0);
/* XXX: scope zone ID? */
ifra.ifra_flags |= (IN6_IFF_AUTOCONF|IN6_IFF_TEMPORARY);
/* allocate ifaddr structure, link into chain, etc. */
updateflags = 0;
if (delay)
updateflags |= IN6_IFAUPDATE_DADDELAY;
if ((error = in6_update_ifa(ifp, &ifra, NULL, updateflags)) != 0)
return (error);
newia = in6ifa_ifpwithaddr(ifp, &ifra.ifra_addr.sin6_addr);
if (newia == NULL) { /* XXX: can it happen? */
nd6log((LOG_ERR,
"%s: ifa update succeeded, but we got no ifaddr\n",
__func__));
return (EINVAL); /* XXX */
}
newia->ia6_ndpr = ia0->ia6_ndpr;
newia->ia6_ndpr->ndpr_addrcnt++;
ifa_free(&newia->ia_ifa);
/*
* A newly added address might affect the status of other addresses.
* XXX: when the temporary address is generated with a new public
* address, the onlink check is redundant. However, it would be safe
* to do the check explicitly everywhere a new address is generated,
* and, in fact, we surely need the check when we create a new
* temporary address due to deprecation of an old temporary address.
*/
pfxlist_onlink_check();
return (0);
}
static int
rt6_deleteroute(const struct rtentry *rt, const struct nhop_object *nh,
void *arg)
{
struct in6_addr *gate = (struct in6_addr *)arg;
int nh_rt_flags;
if (nh->gw_sa.sa_family != AF_INET6)
return (0);
if (!IN6_ARE_ADDR_EQUAL(gate, &nh->gw6_sa.sin6_addr)) {
return (0);
}
/*
* Do not delete a static route.
* XXX: this seems to be a bit ad-hoc. Should we consider the
* 'cloned' bit instead?
*/
nh_rt_flags = nhop_get_rtflags(nh);
if ((nh_rt_flags & RTF_STATIC) != 0)
return (0);
/*
* We delete only host route. This means, in particular, we don't
* delete default route.
*/
if ((nh_rt_flags & RTF_HOST) == 0)
return (0);
return (1);
#undef SIN6
}
/*
* Delete all the routing table entries that use the specified gateway.
* XXX: this function causes search through all entries of routing table, so
* it shouldn't be called when acting as a router.
*/
void
rt6_flush(struct in6_addr *gateway, struct ifnet *ifp)
{
/* We'll care only link-local addresses */
if (!IN6_IS_ADDR_LINKLOCAL(gateway))
return;
/* XXX Do we really need to walk any but the default FIB? */
rib_foreach_table_walk_del(AF_INET6, rt6_deleteroute, (void *)gateway);
}
int
nd6_setdefaultiface(int ifindex)
{
int error = 0;
if (ifindex < 0 || V_if_index < ifindex)
return (EINVAL);
if (ifindex != 0 && !ifnet_byindex(ifindex))
return (EINVAL);
if (V_nd6_defifindex != ifindex) {
V_nd6_defifindex = ifindex;
if (V_nd6_defifindex > 0)
V_nd6_defifp = ifnet_byindex(V_nd6_defifindex);
else
V_nd6_defifp = NULL;
/*
* Our current implementation assumes one-to-one maping between
* interfaces and links, so it would be natural to use the
* default interface as the default link.
*/
scope6_setdefault(V_nd6_defifp);
}
return (error);
}
bool
nd6_defrouter_list_empty(void)
{
return (TAILQ_EMPTY(&V_nd6_defrouter));
}
void
nd6_defrouter_timer(void)
{
struct nd_defrouter *dr, *ndr;
struct nd6_drhead drq;
TAILQ_INIT(&drq);
ND6_WLOCK();
TAILQ_FOREACH_SAFE(dr, &V_nd6_defrouter, dr_entry, ndr)
if (dr->expire && dr->expire < time_uptime)
defrouter_unlink(dr, &drq);
ND6_WUNLOCK();
while ((dr = TAILQ_FIRST(&drq)) != NULL) {
TAILQ_REMOVE(&drq, dr, dr_entry);
defrouter_del(dr);
}
}
/*
* Nuke default router list entries toward ifp.
* We defer removal of default router list entries that is installed in the
* routing table, in order to keep additional side effects as small as possible.
*/
void
nd6_defrouter_purge(struct ifnet *ifp)
{
struct nd_defrouter *dr, *ndr;
struct nd6_drhead drq;
TAILQ_INIT(&drq);
ND6_WLOCK();
TAILQ_FOREACH_SAFE(dr, &V_nd6_defrouter, dr_entry, ndr) {
if (dr->installed)
continue;
if (dr->ifp == ifp)
defrouter_unlink(dr, &drq);
}
TAILQ_FOREACH_SAFE(dr, &V_nd6_defrouter, dr_entry, ndr) {
if (!dr->installed)
continue;
if (dr->ifp == ifp)
defrouter_unlink(dr, &drq);
}
ND6_WUNLOCK();
/* Delete the unlinked router objects. */
while ((dr = TAILQ_FIRST(&drq)) != NULL) {
TAILQ_REMOVE(&drq, dr, dr_entry);
defrouter_del(dr);
}
}
void
nd6_defrouter_flush_all(void)
{
struct nd_defrouter *dr;
struct nd6_drhead drq;
TAILQ_INIT(&drq);
ND6_WLOCK();
while ((dr = TAILQ_FIRST(&V_nd6_defrouter)) != NULL)
defrouter_unlink(dr, &drq);
ND6_WUNLOCK();
while ((dr = TAILQ_FIRST(&drq)) != NULL) {
TAILQ_REMOVE(&drq, dr, dr_entry);
defrouter_del(dr);
}
}
void
nd6_defrouter_init(void)
{
TAILQ_INIT(&V_nd6_defrouter);
}
static int
nd6_sysctl_drlist(SYSCTL_HANDLER_ARGS)
{
struct in6_defrouter d;
struct nd_defrouter *dr;
int error;
if (req->newptr != NULL)
return (EPERM);
error = sysctl_wire_old_buffer(req, 0);
if (error != 0)
return (error);
bzero(&d, sizeof(d));
d.rtaddr.sin6_family = AF_INET6;
d.rtaddr.sin6_len = sizeof(d.rtaddr);
ND6_RLOCK();
TAILQ_FOREACH(dr, &V_nd6_defrouter, dr_entry) {
d.rtaddr.sin6_addr = dr->rtaddr;
error = sa6_recoverscope(&d.rtaddr);
if (error != 0)
break;
d.flags = dr->raflags;
d.rtlifetime = dr->rtlifetime;
d.expire = dr->expire + (time_second - time_uptime);
d.if_index = dr->ifp->if_index;
error = SYSCTL_OUT(req, &d, sizeof(d));
if (error != 0)
break;
}
ND6_RUNLOCK();
return (error);
}
SYSCTL_PROC(_net_inet6_icmp6, ICMPV6CTL_ND6_DRLIST, nd6_drlist,
CTLTYPE_OPAQUE | CTLFLAG_RD | CTLFLAG_MPSAFE,
NULL, 0, nd6_sysctl_drlist, "S,in6_defrouter",
"NDP default router list");
diff --git a/tests/sys/net/routing/test_rtsock_l3.c b/tests/sys/net/routing/test_rtsock_l3.c
index daba6e5013e6..9486ac466965 100644
--- a/tests/sys/net/routing/test_rtsock_l3.c
+++ b/tests/sys/net/routing/test_rtsock_l3.c
@@ -1,1418 +1,1417 @@
/*-
* SPDX-License-Identifier: BSD-2-Clause-FreeBSD
*
* Copyright (c) 2019 Alexander V. Chernikov
*
* 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 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 AUTHOR 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.
*
* $FreeBSD$
*/
#include "rtsock_common.h"
#include "rtsock_config.h"
#include "sys/types.h"
#include <sys/time.h>
#include <sys/ioctl.h>
#include "net/bpf.h"
static void
jump_vnet(struct rtsock_test_config *c, const atf_tc_t *tc)
{
char vnet_name[512];
snprintf(vnet_name, sizeof(vnet_name), "vt-%s", atf_tc_get_ident(tc));
RLOG("jumping to %s", vnet_name);
vnet_switch(vnet_name, c->ifnames, c->num_interfaces);
/* Update ifindex cache */
c->ifindex = if_nametoindex(c->ifname);
}
static inline struct rtsock_test_config *
presetup_ipv6_iface(const atf_tc_t *tc)
{
struct rtsock_test_config *c;
int ret;
c = config_setup(tc, NULL);
jump_vnet(c, tc);
ret = iface_turn_up(c->ifname);
ATF_REQUIRE_MSG(ret == 0, "Unable to turn up %s", c->ifname);
ret = iface_enable_ipv6(c->ifname);
ATF_REQUIRE_MSG(ret == 0, "Unable to enable IPv6 on %s", c->ifname);
return (c);
}
static inline struct rtsock_test_config *
presetup_ipv6(const atf_tc_t *tc)
{
struct rtsock_test_config *c;
int ret;
c = presetup_ipv6_iface(tc);
ret = iface_setup_addr(c->ifname, c->addr6_str, c->plen6);
c->rtsock_fd = rtsock_setup_socket();
return (c);
}
static inline struct rtsock_test_config *
presetup_ipv4_iface(const atf_tc_t *tc)
{
struct rtsock_test_config *c;
int ret;
c = config_setup(tc, NULL);
jump_vnet(c, tc);
ret = iface_turn_up(c->ifname);
ATF_REQUIRE_MSG(ret == 0, "Unable to turn up %s", c->ifname);
return (c);
}
static inline struct rtsock_test_config *
presetup_ipv4(const atf_tc_t *tc)
{
struct rtsock_test_config *c;
int ret;
c = presetup_ipv4_iface(tc);
/* assumes ifconfig doing IFF_UP */
ret = iface_setup_addr(c->ifname, c->addr4_str, c->plen4);
ATF_REQUIRE_MSG(ret == 0, "ifconfig failed");
c->rtsock_fd = rtsock_setup_socket();
return (c);
}
static void
prepare_v4_network(struct rtsock_test_config *c, struct sockaddr_in *dst,
struct sockaddr_in *mask, struct sockaddr_in *gw)
{
/* Create IPv4 subnetwork with smaller prefix */
sa_fill_mask4(mask, c->plen4 + 1);
*dst = c->net4;
/* Calculate GW as last-net-address - 1 */
*gw = c->net4;
gw->sin_addr.s_addr = htonl((ntohl(c->net4.sin_addr.s_addr) | ~ntohl(c->mask4.sin_addr.s_addr)) - 1);
sa_print((struct sockaddr *)dst, 0);
sa_print((struct sockaddr *)mask, 0);
sa_print((struct sockaddr *)gw, 0);
}
static void
prepare_v6_network(struct rtsock_test_config *c, struct sockaddr_in6 *dst,
struct sockaddr_in6 *mask, struct sockaddr_in6 *gw)
{
/* Create IPv6 subnetwork with smaller prefix */
sa_fill_mask6(mask, c->plen6 + 1);
*dst = c->net6;
/* Calculate GW as last-net-address - 1 */
*gw = c->net6;
#define _s6_addr32 __u6_addr.__u6_addr32
gw->sin6_addr._s6_addr32[0] = htonl((ntohl(gw->sin6_addr._s6_addr32[0]) | ~ntohl(c->mask6.sin6_addr._s6_addr32[0])));
gw->sin6_addr._s6_addr32[1] = htonl((ntohl(gw->sin6_addr._s6_addr32[1]) | ~ntohl(c->mask6.sin6_addr._s6_addr32[1])));
gw->sin6_addr._s6_addr32[2] = htonl((ntohl(gw->sin6_addr._s6_addr32[2]) | ~ntohl(c->mask6.sin6_addr._s6_addr32[2])));
gw->sin6_addr._s6_addr32[3] = htonl((ntohl(gw->sin6_addr._s6_addr32[3]) | ~ntohl(c->mask6.sin6_addr._s6_addr32[3])) - 1);
#undef _s6_addr32
sa_print((struct sockaddr *)dst, 0);
sa_print((struct sockaddr *)mask, 0);
sa_print((struct sockaddr *)gw, 0);
}
static void
prepare_route_message(struct rt_msghdr *rtm, int cmd, struct sockaddr *dst,
struct sockaddr *mask, struct sockaddr *gw)
{
rtsock_prepare_route_message(rtm, cmd, dst, mask, gw);
if (cmd == RTM_ADD || cmd == RTM_CHANGE)
rtm->rtm_flags |= RTF_STATIC;
}
static void
verify_route_message(struct rt_msghdr *rtm, int cmd, struct sockaddr *dst,
struct sockaddr *mask, struct sockaddr *gw)
{
char msg[512];
struct sockaddr *sa;
int ret;
RTSOCK_ATF_REQUIRE_MSG(rtm, rtm->rtm_type == cmd,
"expected %s message, got %d (%s)", rtsock_print_cmdtype(cmd),
rtm->rtm_type, rtsock_print_cmdtype(rtm->rtm_type));
RTSOCK_ATF_REQUIRE_MSG(rtm, rtm->rtm_errno == 0,
"got got errno %d as message reply", rtm->rtm_errno);
RTSOCK_ATF_REQUIRE_MSG(rtm, rtm->_rtm_spare1 == 0,
"expected rtm_spare==0, got %d", rtm->_rtm_spare1);
/* kernel MAY return more sockaddrs, including RTA_IFP / RTA_IFA, so verify the needed ones */
if (dst != NULL) {
sa = rtsock_find_rtm_sa(rtm, RTA_DST);
RTSOCK_ATF_REQUIRE_MSG(rtm, sa != NULL, "DST is not set");
ret = sa_equal_msg(sa, dst, msg, sizeof(msg));
RTSOCK_ATF_REQUIRE_MSG(rtm, ret != 0, "DST sa diff: %s", msg);
}
if (mask != NULL) {
sa = rtsock_find_rtm_sa(rtm, RTA_NETMASK);
RTSOCK_ATF_REQUIRE_MSG(rtm, sa != NULL, "NETMASK is not set");
ret = sa_equal_msg(sa, mask, msg, sizeof(msg));
ret = 1;
RTSOCK_ATF_REQUIRE_MSG(rtm, ret != 0, "NETMASK sa diff: %s", msg);
}
if (gw != NULL) {
sa = rtsock_find_rtm_sa(rtm, RTA_GATEWAY);
RTSOCK_ATF_REQUIRE_MSG(rtm, sa != NULL, "GATEWAY is not set");
ret = sa_equal_msg(sa, gw, msg, sizeof(msg));
RTSOCK_ATF_REQUIRE_MSG(rtm, ret != 0, "GATEWAY sa diff: %s", msg);
}
}
static void
verify_route_message_extra(struct rt_msghdr *rtm, int ifindex, int rtm_flags)
{
RTSOCK_ATF_REQUIRE_MSG(rtm, rtm->rtm_index == ifindex,
"expected ifindex %d, got %d", ifindex, rtm->rtm_index);
if (rtm->rtm_flags != rtm_flags) {
char got_flags[64], expected_flags[64];
rtsock_print_rtm_flags(got_flags, sizeof(got_flags),
rtm->rtm_flags);
rtsock_print_rtm_flags(expected_flags, sizeof(expected_flags),
rtm_flags);
RTSOCK_ATF_REQUIRE_MSG(rtm, rtm->rtm_flags == rtm_flags,
"expected flags: 0x%X %s, got 0x%X %s",
rtm_flags, expected_flags,
rtm->rtm_flags, got_flags);
}
}
static void
verify_link_gateway(struct rt_msghdr *rtm, int ifindex)
{
struct sockaddr *sa;
struct sockaddr_dl *sdl;
sa = rtsock_find_rtm_sa(rtm, RTA_GATEWAY);
RTSOCK_ATF_REQUIRE_MSG(rtm, sa != NULL, "GATEWAY is not set");
RTSOCK_ATF_REQUIRE_MSG(rtm, sa->sa_family == AF_LINK, "GW sa family is %d", sa->sa_family);
sdl = (struct sockaddr_dl *)sa;
RTSOCK_ATF_REQUIRE_MSG(rtm, sdl->sdl_index == ifindex, "GW ifindex is %d", sdl->sdl_index);
}
/* TESTS */
#define DECLARE_TEST_VARS \
char buffer[2048]; \
struct rtsock_test_config *c; \
struct rt_msghdr *rtm = (struct rt_msghdr *)buffer; \
struct sockaddr *sa; \
int ret; \
\
#define DESCRIBE_ROOT_TEST(_msg) config_describe_root_test(tc, _msg)
#define CLEANUP_AFTER_TEST config_generic_cleanup(tc)
#define RTM_DECLARE_ROOT_TEST(_name, _descr) \
ATF_TC_WITH_CLEANUP(_name); \
ATF_TC_HEAD(_name, tc) \
{ \
DESCRIBE_ROOT_TEST(_descr); \
} \
ATF_TC_CLEANUP(_name, tc) \
{ \
CLEANUP_AFTER_TEST; \
}
ATF_TC_WITH_CLEANUP(rtm_get_v4_exact_success);
ATF_TC_HEAD(rtm_get_v4_exact_success, tc)
{
DESCRIBE_ROOT_TEST("Tests RTM_GET with exact prefix lookup on an interface prefix");
}
ATF_TC_BODY(rtm_get_v4_exact_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv4(tc);
prepare_route_message(rtm, RTM_GET, (struct sockaddr *)&c->net4,
(struct sockaddr *)&c->mask4, NULL);
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
/*
* RTM_GET: Report Metrics: len 240, pid: 45072, seq 42, errno 0, flags: <UP,DONE,PINNED>
* sockaddrs: 0x7 <DST,GATEWAY,NETMASK>
* af=inet len=16 addr=192.0.2.0 hd={10, 02, 00{2}, C0, 00, 02, 00{9}}
* af=link len=54 sdl_index=3 if_name=tap4242 hd={36, 12, 03, 00, 06, 00{49}}
* af=inet len=16 addr=255.255.255.0 hd={10, 02, FF{5}, 00{9}}
*/
verify_route_message(rtm, RTM_GET, (struct sockaddr *)&c->net4,
(struct sockaddr *)&c->mask4, NULL);
verify_route_message_extra(rtm, c->ifindex, RTF_UP | RTF_DONE | RTF_PINNED);
/* Explicitly verify gateway for the interface route */
verify_link_gateway(rtm, c->ifindex);
sa = rtsock_find_rtm_sa(rtm, RTA_GATEWAY);
RTSOCK_ATF_REQUIRE_MSG(rtm, sa != NULL, "GATEWAY is not set");
RTSOCK_ATF_REQUIRE_MSG(rtm, sa->sa_family == AF_LINK, "GW sa family is %d", sa->sa_family);
struct sockaddr_dl *sdl = (struct sockaddr_dl *)sa;
RTSOCK_ATF_REQUIRE_MSG(rtm, sdl->sdl_index == c->ifindex, "GW ifindex is %d", sdl->sdl_index);
}
ATF_TC_CLEANUP(rtm_get_v4_exact_success, tc)
{
CLEANUP_AFTER_TEST;
}
ATF_TC_WITH_CLEANUP(rtm_get_v4_lpm_success);
ATF_TC_HEAD(rtm_get_v4_lpm_success, tc)
{
DESCRIBE_ROOT_TEST("Tests RTM_GET with address lookup on an existing prefix");
}
ATF_TC_BODY(rtm_get_v4_lpm_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv4(tc);
prepare_route_message(rtm, RTM_GET, (struct sockaddr *)&c->net4, NULL, NULL);
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
/*
* RTM_GET: Report Metrics: len 312, pid: 67074, seq 1, errno 0, flags:<UP,DONE,PINNED>
* locks: inits:
* sockaddrs: <DST,GATEWAY,NETMASK,IFP,IFA>
* 10.0.0.0 link#1 255.255.255.0 vtnet0:52.54.0.42.f.ef 10.0.0.157
*/
verify_route_message(rtm, RTM_GET, (struct sockaddr *)&c->net4,
(struct sockaddr *)&c->mask4, NULL);
verify_route_message_extra(rtm, c->ifindex, RTF_UP | RTF_DONE | RTF_PINNED);
}
ATF_TC_CLEANUP(rtm_get_v4_lpm_success, tc)
{
CLEANUP_AFTER_TEST;
}
ATF_TC_WITH_CLEANUP(rtm_get_v4_empty_dst_failure);
ATF_TC_HEAD(rtm_get_v4_empty_dst_failure, tc)
{
DESCRIBE_ROOT_TEST("Tests RTM_GET with empty DST addr");
}
ATF_TC_BODY(rtm_get_v4_empty_dst_failure, tc)
{
DECLARE_TEST_VARS;
struct rtsock_config_options co;
bzero(&co, sizeof(co));
co.num_interfaces = 0;
c = config_setup(tc,&co);
c->rtsock_fd = rtsock_setup_socket();
rtsock_prepare_route_message(rtm, RTM_GET, NULL,
(struct sockaddr *)&c->mask4, NULL);
rtsock_update_rtm_len(rtm);
ATF_CHECK_ERRNO(EINVAL, write(c->rtsock_fd, rtm, rtm->rtm_msglen));
}
ATF_TC_CLEANUP(rtm_get_v4_empty_dst_failure, tc)
{
CLEANUP_AFTER_TEST;
}
ATF_TC_WITH_CLEANUP(rtm_get_v4_hostbits_failure);
ATF_TC_HEAD(rtm_get_v4_hostbits_failure, tc)
{
DESCRIBE_ROOT_TEST("Tests RTM_GET with prefix with some hosts-bits set");
}
ATF_TC_BODY(rtm_get_v4_hostbits_failure, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv4(tc);
/* Q the same prefix */
rtsock_prepare_route_message(rtm, RTM_GET, (struct sockaddr *)&c->addr4,
(struct sockaddr *)&c->mask4, NULL);
rtsock_update_rtm_len(rtm);
ATF_CHECK_ERRNO(ESRCH, write(c->rtsock_fd, rtm, rtm->rtm_msglen));
}
ATF_TC_CLEANUP(rtm_get_v4_hostbits_failure, tc)
{
CLEANUP_AFTER_TEST;
}
ATF_TC_WITH_CLEANUP(rtm_add_v4_gw_direct_success);
ATF_TC_HEAD(rtm_add_v4_gw_direct_success, tc)
{
DESCRIBE_ROOT_TEST("Tests IPv4 route addition with directly-reachable GW specified by IP");
}
ATF_TC_BODY(rtm_add_v4_gw_direct_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv4(tc);
/* Create IPv4 subnetwork with smaller prefix */
struct sockaddr_in mask4;
struct sockaddr_in net4;
struct sockaddr_in gw4;
prepare_v4_network(c, &net4, &mask4, &gw4);
prepare_route_message(rtm, RTM_ADD, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, (struct sockaddr *)&gw4);
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
/*
* RTM_ADD: Add Route: len 200, pid: 46068, seq 42, errno 0, flags:<GATEWAY,DONE,STATIC>
* locks: inits:
* sockaddrs: <DST,GATEWAY,NETMASK>
* 192.0.2.0 192.0.2.254 255.255.255.128
*/
verify_route_message(rtm, RTM_ADD, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, (struct sockaddr *)&gw4);
verify_route_message_extra(rtm, c->ifindex,
RTF_UP | RTF_DONE | RTF_GATEWAY | RTF_STATIC);
}
ATF_TC_CLEANUP(rtm_add_v4_gw_direct_success, tc)
{
CLEANUP_AFTER_TEST;
}
RTM_DECLARE_ROOT_TEST(rtm_add_v4_no_rtf_host_failure,
"Tests failure with netmask sa and RTF_HOST inconsistency");
ATF_TC_BODY(rtm_add_v4_no_rtf_host_failure, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv4(tc);
/* Create IPv4 subnetwork with smaller prefix */
struct sockaddr_in mask4;
struct sockaddr_in net4;
struct sockaddr_in gw4;
prepare_v4_network(c, &net4, &mask4, &gw4);
prepare_route_message(rtm, RTM_ADD, (struct sockaddr *)&net4,
NULL, (struct sockaddr *)&gw4);
rtsock_update_rtm_len(rtm);
/* RTF_HOST is NOT specified, while netmask is empty */
ATF_CHECK_ERRNO(EINVAL, write(c->rtsock_fd, rtm, rtm->rtm_msglen));
}
ATF_TC_WITH_CLEANUP(rtm_del_v4_prefix_nogw_success);
ATF_TC_HEAD(rtm_del_v4_prefix_nogw_success, tc)
{
DESCRIBE_ROOT_TEST("Tests IPv4 route removal without specifying gateway");
}
ATF_TC_BODY(rtm_del_v4_prefix_nogw_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv4(tc);
/* Create IPv4 subnetwork with smaller prefix */
struct sockaddr_in mask4;
struct sockaddr_in net4;
struct sockaddr_in gw4;
prepare_v4_network(c, &net4, &mask4, &gw4);
prepare_route_message(rtm, RTM_ADD, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, (struct sockaddr *)&gw4);
rtsock_send_rtm(c->rtsock_fd, rtm);
/* Route has been added successfully, try to delete it */
prepare_route_message(rtm, RTM_DELETE, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, NULL);
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
/*
* RTM_DELETE: Delete Route: len 200, pid: 46417, seq 43, errno 0, flags: <GATEWAY,DONE,STATIC>
* sockaddrs: 0x7 <DST,GATEWAY,NETMASK>
* af=inet len=16 addr=192.0.2.0 hd={10, 02, 00{2}, C0, 00, 02, 00{9}}
* af=inet len=16 addr=192.0.2.254 hd={10, 02, 00{2}, C0, 00, 02, FE, 00{8}}
* af=inet len=16 addr=255.255.255.128 hd={10, 02, FF{5}, 80, 00{8}}
*/
verify_route_message(rtm, RTM_DELETE, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, (struct sockaddr *)&gw4);
verify_route_message_extra(rtm, c->ifindex, RTF_DONE | RTF_GATEWAY | RTF_STATIC);
}
ATF_TC_CLEANUP(rtm_del_v4_prefix_nogw_success, tc)
{
CLEANUP_AFTER_TEST;
}
RTM_DECLARE_ROOT_TEST(rtm_change_v4_gw_success,
"Tests IPv4 gateway change");
ATF_TC_BODY(rtm_change_v4_gw_success, tc)
{
DECLARE_TEST_VARS;
struct rtsock_config_options co;
bzero(&co, sizeof(co));
co.num_interfaces = 2;
c = config_setup(tc, &co);
jump_vnet(c, tc);
ret = iface_turn_up(c->ifnames[0]);
ATF_REQUIRE_MSG(ret == 0, "Unable to turn up %s", c->ifnames[0]);
ret = iface_turn_up(c->ifnames[1]);
ATF_REQUIRE_MSG(ret == 0, "Unable to turn up %s", c->ifnames[1]);
ret = iface_setup_addr(c->ifnames[0], c->addr4_str, c->plen4);
ATF_REQUIRE_MSG(ret == 0, "ifconfig failed");
/* Use 198.51.100.0/24 "TEST-NET-2" for the second interface */
ret = iface_setup_addr(c->ifnames[1], "198.51.100.1", 24);
ATF_REQUIRE_MSG(ret == 0, "ifconfig failed");
c->rtsock_fd = rtsock_setup_socket();
/* Create IPv4 subnetwork with smaller prefix */
struct sockaddr_in mask4;
struct sockaddr_in net4;
struct sockaddr_in gw4;
prepare_v4_network(c, &net4, &mask4, &gw4);
prepare_route_message(rtm, RTM_ADD, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, (struct sockaddr *)&gw4);
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
verify_route_message(rtm, RTM_ADD, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, (struct sockaddr *)&gw4);
/* Change gateway to the one on desiding on the other interface */
inet_pton(AF_INET, "198.51.100.2", &gw4.sin_addr.s_addr);
prepare_route_message(rtm, RTM_CHANGE, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, (struct sockaddr *)&gw4);
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
verify_route_message(rtm, RTM_CHANGE, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, (struct sockaddr *)&gw4);
verify_route_message_extra(rtm, if_nametoindex(c->ifnames[1]),
RTF_UP | RTF_DONE | RTF_GATEWAY | RTF_STATIC);
/* Verify the change has actually taken place */
prepare_route_message(rtm, RTM_GET, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, NULL);
rtsock_send_rtm(c->rtsock_fd, rtm);
/*
* RTM_GET: len 200, pid: 3894, seq 44, errno 0, flags: <UP,GATEWAY,DONE,STATIC>
* sockaddrs: 0x7 <DST,GATEWAY,NETMASK>
* af=inet len=16 addr=192.0.2.0 hd={x10, x02, x00{2}, xC0, x00, x02, x00{9}}
* af=inet len=16 addr=198.51.100.2 hd={x10, x02, x00{2}, xC6, x33, x64, x02, x00{8}}
* af=inet len=16 addr=255.255.255.128 hd={x10, x02, xFF, xFF, xFF, xFF, xFF, x80, x00{8}}
*/
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
verify_route_message_extra(rtm, if_nametoindex(c->ifnames[1]),
RTF_UP | RTF_DONE | RTF_GATEWAY | RTF_STATIC);
}
RTM_DECLARE_ROOT_TEST(rtm_change_v4_mtu_success,
"Tests IPv4 path mtu change");
ATF_TC_BODY(rtm_change_v4_mtu_success, tc)
{
DECLARE_TEST_VARS;
unsigned long test_mtu = 1442;
c = presetup_ipv4(tc);
/* Create IPv4 subnetwork with smaller prefix */
struct sockaddr_in mask4;
struct sockaddr_in net4;
struct sockaddr_in gw4;
prepare_v4_network(c, &net4, &mask4, &gw4);
prepare_route_message(rtm, RTM_ADD, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, (struct sockaddr *)&gw4);
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
/* Change MTU */
prepare_route_message(rtm, RTM_CHANGE, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, NULL);
rtm->rtm_inits |= RTV_MTU;
rtm->rtm_rmx.rmx_mtu = test_mtu;
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
verify_route_message(rtm, RTM_CHANGE, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, NULL);
RTSOCK_ATF_REQUIRE_MSG(rtm, rtm->rtm_rmx.rmx_mtu == test_mtu,
"expected mtu: %lu, got %lu", test_mtu, rtm->rtm_rmx.rmx_mtu);
/* Verify the change has actually taken place */
prepare_route_message(rtm, RTM_GET, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, NULL);
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
RTSOCK_ATF_REQUIRE_MSG(rtm, rtm->rtm_rmx.rmx_mtu == test_mtu,
"expected mtu: %lu, got %lu", test_mtu, rtm->rtm_rmx.rmx_mtu);
}
RTM_DECLARE_ROOT_TEST(rtm_change_v4_flags_success,
"Tests IPv4 path flags change");
ATF_TC_BODY(rtm_change_v4_flags_success, tc)
{
DECLARE_TEST_VARS;
uint32_t test_flags = RTF_PROTO1 | RTF_PROTO2 | RTF_PROTO3 | RTF_STATIC;
uint32_t desired_flags;
c = presetup_ipv4(tc);
/* Create IPv4 subnetwork with smaller prefix */
struct sockaddr_in mask4;
struct sockaddr_in net4;
struct sockaddr_in gw4;
prepare_v4_network(c, &net4, &mask4, &gw4);
prepare_route_message(rtm, RTM_ADD, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, (struct sockaddr *)&gw4);
/* Set test flags during route addition */
desired_flags = RTF_UP | RTF_DONE | RTF_GATEWAY | test_flags;
rtm->rtm_flags |= test_flags;
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
/* Change flags */
prepare_route_message(rtm, RTM_CHANGE, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, NULL);
rtm->rtm_flags &= ~test_flags;
desired_flags &= ~test_flags;
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
/* Verify updated flags */
verify_route_message_extra(rtm, c->ifindex, desired_flags | RTF_DONE);
/* Verify the change has actually taken place */
prepare_route_message(rtm, RTM_GET, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, NULL);
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
verify_route_message_extra(rtm, c->ifindex, desired_flags | RTF_DONE);
}
ATF_TC_WITH_CLEANUP(rtm_add_v6_gu_gw_gu_direct_success);
ATF_TC_HEAD(rtm_add_v6_gu_gw_gu_direct_success, tc)
{
DESCRIBE_ROOT_TEST("Tests IPv6 global unicast prefix addition with directly-reachable GU GW");
}
ATF_TC_BODY(rtm_add_v6_gu_gw_gu_direct_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv6(tc);
/* Create IPv6 subnetwork with smaller prefix */
struct sockaddr_in6 mask6;
struct sockaddr_in6 net6;
struct sockaddr_in6 gw6;
prepare_v6_network(c, &net6, &mask6, &gw6);
prepare_route_message(rtm, RTM_ADD, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, (struct sockaddr *)&gw6);
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
/*
* RTM_ADD: Add Route: len 200, pid: 46068, seq 42, errno 0, flags:<GATEWAY,DONE,STATIC>
* locks: inits:
* sockaddrs: <DST,GATEWAY,NETMASK>
* 192.0.2.0 192.0.2.254 255.255.255.128
*/
verify_route_message(rtm, RTM_ADD, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, (struct sockaddr *)&gw6);
verify_route_message_extra(rtm, c->ifindex,
RTF_UP | RTF_DONE | RTF_GATEWAY | RTF_STATIC);
}
ATF_TC_CLEANUP(rtm_add_v6_gu_gw_gu_direct_success, tc)
{
CLEANUP_AFTER_TEST;
}
ATF_TC_WITH_CLEANUP(rtm_del_v6_gu_prefix_nogw_success);
ATF_TC_HEAD(rtm_del_v6_gu_prefix_nogw_success, tc)
{
DESCRIBE_ROOT_TEST("Tests IPv6 global unicast prefix removal without specifying gateway");
}
ATF_TC_BODY(rtm_del_v6_gu_prefix_nogw_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv6(tc);
/* Create IPv6 subnetwork with smaller prefix */
struct sockaddr_in6 mask6;
struct sockaddr_in6 net6;
struct sockaddr_in6 gw6;
prepare_v6_network(c, &net6, &mask6, &gw6);
prepare_route_message(rtm, RTM_ADD, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, (struct sockaddr *)&gw6);
rtsock_send_rtm(c->rtsock_fd, rtm);
/* Route has been added successfully, try to delete it */
prepare_route_message(rtm, RTM_DELETE, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, NULL);
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
/*
* RTM_DELETE: Delete Route: len 200, pid: 46417, seq 43, errno 0, flags: <GATEWAY,DONE,STATIC>
* sockaddrs: 0x7 <DST,GATEWAY,NETMASK>
* af=inet len=16 addr=192.0.2.0 hd={10, 02, 00{2}, C0, 00, 02, 00{9}}
* af=inet len=16 addr=192.0.2.254 hd={10, 02, 00{2}, C0, 00, 02, FE, 00{8}}
* af=inet len=16 addr=255.255.255.128 hd={10, 02, FF{5}, 80, 00{8}}
*/
verify_route_message(rtm, RTM_DELETE, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, (struct sockaddr *)&gw6);
verify_route_message_extra(rtm, c->ifindex, RTF_DONE | RTF_GATEWAY | RTF_STATIC);
}
ATF_TC_CLEANUP(rtm_del_v6_gu_prefix_nogw_success, tc)
{
CLEANUP_AFTER_TEST;
}
RTM_DECLARE_ROOT_TEST(rtm_change_v6_gw_success,
"Tests IPv6 gateway change");
ATF_TC_BODY(rtm_change_v6_gw_success, tc)
{
DECLARE_TEST_VARS;
struct rtsock_config_options co;
bzero(&co, sizeof(co));
co.num_interfaces = 2;
c = config_setup(tc, &co);
jump_vnet(c, tc);
ret = iface_turn_up(c->ifnames[0]);
ATF_REQUIRE_MSG(ret == 0, "Unable to turn up %s", c->ifnames[0]);
ret = iface_turn_up(c->ifnames[1]);
ATF_REQUIRE_MSG(ret == 0, "Unable to turn up %s", c->ifnames[1]);
ret = iface_enable_ipv6(c->ifnames[0]);
ATF_REQUIRE_MSG(ret == 0, "Unable to enable IPv6 on %s", c->ifnames[0]);
ret = iface_enable_ipv6(c->ifnames[1]);
ATF_REQUIRE_MSG(ret == 0, "Unable to enable IPv6 on %s", c->ifnames[1]);
ret = iface_setup_addr(c->ifnames[0], c->addr6_str, c->plen6);
ATF_REQUIRE_MSG(ret == 0, "ifconfig failed");
ret = iface_setup_addr(c->ifnames[1], "2001:DB8:4242::1", 64);
ATF_REQUIRE_MSG(ret == 0, "ifconfig failed");
c->rtsock_fd = rtsock_setup_socket();
/* Create IPv6 subnetwork with smaller prefix */
struct sockaddr_in6 mask6;
struct sockaddr_in6 net6;
struct sockaddr_in6 gw6;
prepare_v6_network(c, &net6, &mask6, &gw6);
prepare_route_message(rtm, RTM_ADD, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, (struct sockaddr *)&gw6);
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
verify_route_message(rtm, RTM_ADD, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, (struct sockaddr *)&gw6);
/* Change gateway to the one on residing on the other interface */
inet_pton(AF_INET6, "2001:DB8:4242::4242", &gw6.sin6_addr);
prepare_route_message(rtm, RTM_CHANGE, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, (struct sockaddr *)&gw6);
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
verify_route_message(rtm, RTM_CHANGE, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, (struct sockaddr *)&gw6);
verify_route_message_extra(rtm, if_nametoindex(c->ifnames[1]),
RTF_UP | RTF_DONE | RTF_GATEWAY | RTF_STATIC);
/* Verify the change has actually taken place */
prepare_route_message(rtm, RTM_GET, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, NULL);
rtsock_send_rtm(c->rtsock_fd, rtm);
/*
* RTM_GET: len 248, pid: 2268, seq 44, errno 0, flags: <UP,GATEWAY,DONE,STATIC>
* sockaddrs: 0x7 <DST,GATEWAY,NETMASK>
* af=inet6 len=28 addr=2001:db8:: hd={x1C, x1C, x00{6}, x20, x01, x0D, xB8, x00{16}}
* af=inet6 len=28 addr=2001:db8:4242::4242 hd={x1C, x1C, x00{6}, x20, x01, x0D, xB8, x42, x42, x00{8}, x42, x42, x00{4}}
* af=inet6 len=28 addr=ffff:ffff:8000:: hd={x1C, x1C, xFF, xFF, xFF, xFF, xFF, xFF, xFF, xFF, xFF, xFF, x80, x00{15}}
*/
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
verify_route_message_extra(rtm, if_nametoindex(c->ifnames[1]),
RTF_UP | RTF_DONE | RTF_GATEWAY | RTF_STATIC);
}
RTM_DECLARE_ROOT_TEST(rtm_change_v6_mtu_success,
"Tests IPv6 path mtu change");
ATF_TC_BODY(rtm_change_v6_mtu_success, tc)
{
DECLARE_TEST_VARS;
unsigned long test_mtu = 1442;
c = presetup_ipv6(tc);
/* Create IPv6 subnetwork with smaller prefix */
struct sockaddr_in6 mask6;
struct sockaddr_in6 net6;
struct sockaddr_in6 gw6;
prepare_v6_network(c, &net6, &mask6, &gw6);
prepare_route_message(rtm, RTM_ADD, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, (struct sockaddr *)&gw6);
/* Send route add */
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
/* Change MTU */
prepare_route_message(rtm, RTM_CHANGE, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, NULL);
rtm->rtm_inits |= RTV_MTU;
rtm->rtm_rmx.rmx_mtu = test_mtu;
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
verify_route_message(rtm, RTM_CHANGE, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, NULL);
RTSOCK_ATF_REQUIRE_MSG(rtm, rtm->rtm_rmx.rmx_mtu == test_mtu,
"expected mtu: %lu, got %lu", test_mtu, rtm->rtm_rmx.rmx_mtu);
/* Verify the change has actually taken place */
prepare_route_message(rtm, RTM_GET, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, NULL);
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
RTSOCK_ATF_REQUIRE_MSG(rtm, rtm->rtm_rmx.rmx_mtu == test_mtu,
"expected mtu: %lu, got %lu", test_mtu, rtm->rtm_rmx.rmx_mtu);
}
RTM_DECLARE_ROOT_TEST(rtm_change_v6_flags_success,
"Tests IPv6 path flags change");
ATF_TC_BODY(rtm_change_v6_flags_success, tc)
{
DECLARE_TEST_VARS;
uint32_t test_flags = RTF_PROTO1 | RTF_PROTO2 | RTF_PROTO3 | RTF_STATIC;
uint32_t desired_flags;
c = presetup_ipv6(tc);
/* Create IPv6 subnetwork with smaller prefix */
struct sockaddr_in6 mask6;
struct sockaddr_in6 net6;
struct sockaddr_in6 gw6;
prepare_v6_network(c, &net6, &mask6, &gw6);
prepare_route_message(rtm, RTM_ADD, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, (struct sockaddr *)&gw6);
/* Set test flags during route addition */
desired_flags = RTF_UP | RTF_DONE | RTF_GATEWAY | test_flags;
rtm->rtm_flags |= test_flags;
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
/* Change flags */
prepare_route_message(rtm, RTM_CHANGE, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, NULL);
rtm->rtm_flags &= ~test_flags;
desired_flags &= ~test_flags;
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
/* Verify updated flags */
verify_route_message_extra(rtm, c->ifindex, desired_flags | RTF_DONE);
/* Verify the change has actually taken place */
prepare_route_message(rtm, RTM_GET, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, NULL);
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
verify_route_message_extra(rtm, c->ifindex, desired_flags | RTF_DONE);
}
ATF_TC_WITH_CLEANUP(rtm_add_v4_temporal1_success);
ATF_TC_HEAD(rtm_add_v4_temporal1_success, tc)
{
DESCRIBE_ROOT_TEST("Tests IPv4 route expiration with expire time set");
}
ATF_TC_BODY(rtm_add_v4_temporal1_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv4(tc);
/* Create IPv4 subnetwork with smaller prefix */
struct sockaddr_in mask4;
struct sockaddr_in net4;
struct sockaddr_in gw4;
prepare_v4_network(c, &net4, &mask4, &gw4);
prepare_route_message(rtm, RTM_ADD, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, (struct sockaddr *)&gw4);
/* Set expire time to now */
struct timeval tv;
gettimeofday(&tv, NULL);
rtm->rtm_rmx.rmx_expire = tv.tv_sec - 1;
rtm->rtm_inits |= RTV_EXPIRE;
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
ATF_REQUIRE_MSG(rtm != NULL, "unable to get rtsock reply for RTM_ADD");
RTSOCK_ATF_REQUIRE_MSG(rtm, rtm->rtm_inits & RTV_EXPIRE, "RTV_EXPIRE not set");
/* The next should be route deletion */
rtm = rtsock_read_rtm(c->rtsock_fd, buffer, sizeof(buffer));
verify_route_message(rtm, RTM_DELETE, (struct sockaddr *)&net4,
(struct sockaddr *)&mask4, (struct sockaddr *)&gw4);
verify_route_message_extra(rtm, c->ifindex,
RTF_DONE | RTF_GATEWAY | RTF_STATIC);
}
ATF_TC_CLEANUP(rtm_add_v4_temporal1_success, tc)
{
CLEANUP_AFTER_TEST;
}
ATF_TC_WITH_CLEANUP(rtm_add_v6_temporal1_success);
ATF_TC_HEAD(rtm_add_v6_temporal1_success, tc)
{
DESCRIBE_ROOT_TEST("Tests IPv6 global unicast prefix addition with directly-reachable GU GW");
}
ATF_TC_BODY(rtm_add_v6_temporal1_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv6(tc);
/* Create IPv6 subnetwork with smaller prefix */
struct sockaddr_in6 mask6;
struct sockaddr_in6 net6;
struct sockaddr_in6 gw6;
prepare_v6_network(c, &net6, &mask6, &gw6);
prepare_route_message(rtm, RTM_ADD, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, (struct sockaddr *)&gw6);
/* Set expire time to now */
struct timeval tv;
gettimeofday(&tv, NULL);
rtm->rtm_rmx.rmx_expire = tv.tv_sec - 1;
rtm->rtm_inits |= RTV_EXPIRE;
rtsock_send_rtm(c->rtsock_fd, rtm);
rtm = rtsock_read_rtm_reply(c->rtsock_fd, buffer, sizeof(buffer), rtm->rtm_seq);
ATF_REQUIRE_MSG(rtm != NULL, "unable to get rtsock reply for RTM_ADD");
RTSOCK_ATF_REQUIRE_MSG(rtm, rtm->rtm_inits & RTV_EXPIRE, "RTV_EXPIRE not set");
/* The next should be route deletion */
rtm = rtsock_read_rtm(c->rtsock_fd, buffer, sizeof(buffer));
verify_route_message(rtm, RTM_DELETE, (struct sockaddr *)&net6,
(struct sockaddr *)&mask6, (struct sockaddr *)&gw6);
verify_route_message_extra(rtm, c->ifindex,
RTF_DONE | RTF_GATEWAY | RTF_STATIC);
}
ATF_TC_CLEANUP(rtm_add_v6_temporal1_success, tc)
{
CLEANUP_AFTER_TEST;
}
/* Interface address messages tests */
RTM_DECLARE_ROOT_TEST(rtm_add_v6_gu_ifa_hostroute_success,
"Tests validness for /128 host route announce after ifaddr assignment");
ATF_TC_BODY(rtm_add_v6_gu_ifa_hostroute_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv6_iface(tc);
c->rtsock_fd = rtsock_setup_socket();
ret = iface_setup_addr(c->ifname, c->addr6_str, c->plen6);
/*
* There will be multiple.
* RTM_ADD without llinfo.
*/
while (true) {
rtm = rtsock_read_rtm(c->rtsock_fd, buffer, sizeof(buffer));
if ((rtm->rtm_type == RTM_ADD) && ((rtm->rtm_flags & RTF_LLINFO) == 0))
break;
}
/* This should be a message for the host route */
verify_route_message(rtm, RTM_ADD, (struct sockaddr *)&c->addr6, NULL, NULL);
rtsock_validate_pid_kernel(rtm);
/* No netmask should be set */
RTSOCK_ATF_REQUIRE_MSG(rtm, rtsock_find_rtm_sa(rtm, RTA_NETMASK) == NULL, "netmask is set");
/* gateway should be link sdl with ifindex of an address interface */
verify_link_gateway(rtm, c->ifindex);
int expected_rt_flags = RTF_UP | RTF_HOST | RTF_DONE | RTF_STATIC | RTF_PINNED;
verify_route_message_extra(rtm, if_nametoindex("lo0"), expected_rt_flags);
}
RTM_DECLARE_ROOT_TEST(rtm_add_v6_gu_ifa_prefixroute_success,
"Tests validness for the prefix route announce after ifaddr assignment");
ATF_TC_BODY(rtm_add_v6_gu_ifa_prefixroute_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv6_iface(tc);
c->rtsock_fd = rtsock_setup_socket();
ret = iface_setup_addr(c->ifname, c->addr6_str, c->plen6);
/*
* Multiple RTM_ADD messages will be generated:
* 1) lladdr mapping (RTF_LLDATA)
* 2) host route (one w/o netmask)
* 3) prefix route
*/
while (true) {
rtm = rtsock_read_rtm(c->rtsock_fd, buffer, sizeof(buffer));
/* Find RTM_ADD with netmask - this should skip both host route and LLADDR */
if ((rtm->rtm_type == RTM_ADD) && (rtsock_find_rtm_sa(rtm, RTA_NETMASK)))
break;
}
/* This should be a message for the prefix route */
verify_route_message(rtm, RTM_ADD, (struct sockaddr *)&c->net6,
(struct sockaddr *)&c->mask6, NULL);
/* gateway should be link sdl with ifindex of an address interface */
verify_link_gateway(rtm, c->ifindex);
- /* TODO: PINNED? */
- int expected_rt_flags = RTF_UP | RTF_DONE;
+ int expected_rt_flags = RTF_UP | RTF_DONE | RTF_PINNED;
verify_route_message_extra(rtm, c->ifindex, expected_rt_flags);
}
RTM_DECLARE_ROOT_TEST(rtm_add_v6_gu_ifa_ordered_success,
"Tests ordering of the messages for IPv6 global unicast ifaddr assignment");
ATF_TC_BODY(rtm_add_v6_gu_ifa_ordered_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv6_iface(tc);
c->rtsock_fd = rtsock_setup_socket();
ret = iface_setup_addr(c->ifname, c->addr6_str, c->plen6);
int count = 0, tries = 0;
enum msgtype {
MSG_IFADDR,
MSG_HOSTROUTE,
MSG_PREFIXROUTE,
MSG_MAX,
};
int msg_array[MSG_MAX];
bzero(msg_array, sizeof(msg_array));
while (count < 3 && tries < 20) {
rtm = rtsock_read_rtm(c->rtsock_fd, buffer, sizeof(buffer));
tries++;
/* Classify */
if (rtm->rtm_type == RTM_NEWADDR) {
RLOG("MSG_IFADDR: %d", count);
msg_array[MSG_IFADDR] = count++;
continue;
}
/* Find RTM_ADD with netmask - this should skip both host route and LLADDR */
if ((rtm->rtm_type == RTM_ADD) && (rtsock_find_rtm_sa(rtm, RTA_NETMASK))) {
RLOG("MSG_PREFIXROUTE: %d", count);
msg_array[MSG_PREFIXROUTE] = count++;
continue;
}
if ((rtm->rtm_type == RTM_ADD) && ((rtm->rtm_flags & RTF_LLDATA) == 0)) {
RLOG("MSG_HOSTROUTE: %d", count);
msg_array[MSG_HOSTROUTE] = count++;
continue;
}
RLOG("skipping msg type %s, try: %d", rtsock_print_cmdtype(rtm->rtm_type),
tries);
}
/* TODO: verify multicast */
ATF_REQUIRE_MSG(count == 3, "Received only %d/3 messages", count);
ATF_REQUIRE_MSG(msg_array[MSG_IFADDR] == 0, "ifaddr message is not the first");
}
RTM_DECLARE_ROOT_TEST(rtm_del_v6_gu_ifa_hostroute_success,
"Tests validness for /128 host route removal after ifaddr removal");
ATF_TC_BODY(rtm_del_v6_gu_ifa_hostroute_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv6_iface(tc);
ret = iface_setup_addr(c->ifname, c->addr6_str, c->plen6);
c->rtsock_fd = rtsock_setup_socket();
ret = iface_delete_addr(c->ifname, c->addr6_str);
while (true) {
rtm = rtsock_read_rtm(c->rtsock_fd, buffer, sizeof(buffer));
if ((rtm->rtm_type == RTM_DELETE) &&
((rtm->rtm_flags & RTF_LLINFO) == 0) &&
rtsock_find_rtm_sa(rtm, RTA_NETMASK) == NULL)
break;
}
/* This should be a message for the host route */
verify_route_message(rtm, RTM_DELETE, (struct sockaddr *)&c->addr6, NULL, NULL);
rtsock_validate_pid_kernel(rtm);
/* No netmask should be set */
RTSOCK_ATF_REQUIRE_MSG(rtm, rtsock_find_rtm_sa(rtm, RTA_NETMASK) == NULL, "netmask is set");
/* gateway should be link sdl with ifindex of an address interface */
verify_link_gateway(rtm, c->ifindex);
/* XXX: consider passing ifindex in rtm_index as done in RTM_ADD. */
int expected_rt_flags = RTF_HOST | RTF_DONE | RTF_STATIC | RTF_PINNED;
RTSOCK_ATF_REQUIRE_MSG(rtm, rtm->rtm_flags == expected_rt_flags,
"expected rtm flags: 0x%X, got 0x%X", expected_rt_flags, rtm->rtm_flags);
}
RTM_DECLARE_ROOT_TEST(rtm_del_v6_gu_ifa_prefixroute_success,
"Tests validness for the prefix route removal after ifaddr assignment");
ATF_TC_BODY(rtm_del_v6_gu_ifa_prefixroute_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv6_iface(tc);
ret = iface_setup_addr(c->ifname, c->addr6_str, c->plen6);
c->rtsock_fd = rtsock_setup_socket();
ret = iface_delete_addr(c->ifname, c->addr6_str);
while (true) {
rtm = rtsock_read_rtm(c->rtsock_fd, buffer, sizeof(buffer));
/* Find RTM_DELETE with netmask - this should skip both host route and LLADDR */
if ((rtm->rtm_type == RTM_DELETE) && (rtsock_find_rtm_sa(rtm, RTA_NETMASK)))
break;
}
/* This should be a message for the prefix route */
verify_route_message(rtm, RTM_DELETE, (struct sockaddr *)&c->net6,
(struct sockaddr *)&c->mask6, NULL);
/* gateway should be link sdl with ifindex of an address interface */
verify_link_gateway(rtm, c->ifindex);
- int expected_rt_flags = RTF_DONE;
+ int expected_rt_flags = RTF_DONE | RTF_PINNED;
verify_route_message_extra(rtm, c->ifindex, expected_rt_flags);
}
RTM_DECLARE_ROOT_TEST(rtm_add_v4_gu_ifa_prefixroute_success,
"Tests validness for the prefix route announce after ifaddr assignment");
ATF_TC_BODY(rtm_add_v4_gu_ifa_prefixroute_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv4_iface(tc);
c->rtsock_fd = rtsock_setup_socket();
ret = iface_setup_addr(c->ifname, c->addr6_str, c->plen6);
/*
* Multiple RTM_ADD messages will be generated:
* 1) lladdr mapping (RTF_LLDATA)
* 3) prefix route
*/
while (true) {
rtm = rtsock_read_rtm(c->rtsock_fd, buffer, sizeof(buffer));
/* Find RTM_ADD with netmask - this should skip both host route and LLADDR */
if ((rtm->rtm_type == RTM_ADD) && (rtsock_find_rtm_sa(rtm, RTA_NETMASK)))
break;
}
/* This should be a message for the prefix route */
verify_route_message(rtm, RTM_ADD, (struct sockaddr *)&c->net4,
(struct sockaddr *)&c->mask4, NULL);
/* gateway should be link sdl with ifindex of an address interface */
verify_link_gateway(rtm, c->ifindex);
int expected_rt_flags = RTF_UP | RTF_DONE | RTF_PINNED;
verify_route_message_extra(rtm, c->ifindex, expected_rt_flags);
}
RTM_DECLARE_ROOT_TEST(rtm_add_v4_gu_ifa_ordered_success,
"Tests ordering of the messages for IPv4 unicast ifaddr assignment");
ATF_TC_BODY(rtm_add_v4_gu_ifa_ordered_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv4_iface(tc);
c->rtsock_fd = rtsock_setup_socket();
ret = iface_setup_addr(c->ifname, c->addr4_str, c->plen4);
int count = 0, tries = 0;
enum msgtype {
MSG_IFADDR,
MSG_PREFIXROUTE,
MSG_MAX,
};
int msg_array[MSG_MAX];
bzero(msg_array, sizeof(msg_array));
while (count < 2 && tries < 20) {
rtm = rtsock_read_rtm(c->rtsock_fd, buffer, sizeof(buffer));
tries++;
/* Classify */
if (rtm->rtm_type == RTM_NEWADDR) {
RLOG("MSG_IFADDR: %d", count);
msg_array[MSG_IFADDR] = count++;
continue;
}
/* Find RTM_ADD with netmask - this should skip both host route and LLADDR */
if ((rtm->rtm_type == RTM_ADD) && (rtsock_find_rtm_sa(rtm, RTA_NETMASK))) {
RLOG("MSG_PREFIXROUTE: %d", count);
msg_array[MSG_PREFIXROUTE] = count++;
continue;
}
RLOG("skipping msg type %s, try: %d", rtsock_print_cmdtype(rtm->rtm_type),
tries);
}
/* TODO: verify multicast */
ATF_REQUIRE_MSG(count == 2, "Received only %d/2 messages", count);
ATF_REQUIRE_MSG(msg_array[MSG_IFADDR] == 0, "ifaddr message is not the first");
}
RTM_DECLARE_ROOT_TEST(rtm_del_v4_gu_ifa_prefixroute_success,
"Tests validness for the prefix route removal after ifaddr assignment");
ATF_TC_BODY(rtm_del_v4_gu_ifa_prefixroute_success, tc)
{
DECLARE_TEST_VARS;
c = presetup_ipv4_iface(tc);
ret = iface_setup_addr(c->ifname, c->addr4_str, c->plen4);
c->rtsock_fd = rtsock_setup_socket();
ret = iface_delete_addr(c->ifname, c->addr4_str);
while (true) {
rtm = rtsock_read_rtm(c->rtsock_fd, buffer, sizeof(buffer));
/* Find RTM_ADD with netmask - this should skip both host route and LLADDR */
if ((rtm->rtm_type == RTM_DELETE) && (rtsock_find_rtm_sa(rtm, RTA_NETMASK)))
break;
}
/* This should be a message for the prefix route */
verify_route_message(rtm, RTM_DELETE, (struct sockaddr *)&c->net4,
(struct sockaddr *)&c->mask4, NULL);
/* gateway should be link sdl with ifindex of an address interface */
verify_link_gateway(rtm, c->ifindex);
int expected_rt_flags = RTF_DONE | RTF_PINNED;
verify_route_message_extra(rtm, c->ifindex, expected_rt_flags);
}
ATF_TP_ADD_TCS(tp)
{
ATF_TP_ADD_TC(tp, rtm_get_v4_exact_success);
ATF_TP_ADD_TC(tp, rtm_get_v4_lpm_success);
ATF_TP_ADD_TC(tp, rtm_get_v4_hostbits_failure);
ATF_TP_ADD_TC(tp, rtm_get_v4_empty_dst_failure);
ATF_TP_ADD_TC(tp, rtm_add_v4_no_rtf_host_failure);
ATF_TP_ADD_TC(tp, rtm_add_v4_gw_direct_success);
ATF_TP_ADD_TC(tp, rtm_del_v4_prefix_nogw_success);
ATF_TP_ADD_TC(tp, rtm_add_v6_gu_gw_gu_direct_success);
ATF_TP_ADD_TC(tp, rtm_del_v6_gu_prefix_nogw_success);
ATF_TP_ADD_TC(tp, rtm_change_v4_gw_success);
ATF_TP_ADD_TC(tp, rtm_change_v4_mtu_success);
ATF_TP_ADD_TC(tp, rtm_change_v4_flags_success);
ATF_TP_ADD_TC(tp, rtm_change_v6_gw_success);
ATF_TP_ADD_TC(tp, rtm_change_v6_mtu_success);
ATF_TP_ADD_TC(tp, rtm_change_v6_flags_success);
/* ifaddr tests */
ATF_TP_ADD_TC(tp, rtm_add_v6_gu_ifa_hostroute_success);
ATF_TP_ADD_TC(tp, rtm_add_v6_gu_ifa_prefixroute_success);
ATF_TP_ADD_TC(tp, rtm_add_v6_gu_ifa_ordered_success);
ATF_TP_ADD_TC(tp, rtm_del_v6_gu_ifa_hostroute_success);
ATF_TP_ADD_TC(tp, rtm_del_v6_gu_ifa_prefixroute_success);
ATF_TP_ADD_TC(tp, rtm_add_v4_gu_ifa_ordered_success);
ATF_TP_ADD_TC(tp, rtm_del_v4_gu_ifa_prefixroute_success);
/* temporal routes */
ATF_TP_ADD_TC(tp, rtm_add_v4_temporal1_success);
ATF_TP_ADD_TC(tp, rtm_add_v6_temporal1_success);
return (atf_no_error());
}