mcast.c

linux 内核源代码

/*
 *	Multicast support for IPv6
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<[e-mail]>
 *
 *	$Id: mcast.c,v 1.40 2002/02/08 03:57:19 davem Exp $
 *
 *	Based on linux/ipv4/igmp.c and linux/ipv4/ip_sockglue.c
 *
 *	This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 */

/* Changes:
 *
 *	yoshfuji	: fix format of router-alert option
 *	YOSHIFUJI Hideaki @USAGI:
 *		Fixed source address for MLD message based on
 *		<draft-ietf-magma-mld-source-05.txt>.
 *	YOSHIFUJI Hideaki @USAGI:
 *		- Ignore Queries for invalid addresses.
 *		- MLD for link-local addresses.
 *	David L Stevens <[e-mail]>:
 *		- MLDv2 support
 */

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/jiffies.h>
#include <linux/times.h>
#include <linux/net.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/route.h>
#include <linux/init.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>

#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>

#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/snmp.h>

#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/if_inet6.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/ip6_route.h>

#include <net/ip6_checksum.h>

/* Set to 3 to get tracing... */
#define MCAST_DEBUG 2

#if MCAST_DEBUG >= 3
#define MDBG(x) printk x
#else
#define MDBG(x)
#endif

/*
 *  These header formats should be in a separate include file, but icmpv6.h
 *  doesn't have in6_addr defined in all cases, there is no __u128, and no
 *  other files reference these.
 *
 *  			+-DLS 4/14/03
 */

/* Multicast Listener Discovery version 2 headers */

struct mld2_grec {
	__u8		grec_type;
	__u8		grec_auxwords;
	__be16		grec_nsrcs;
	struct in6_addr	grec_mca;
	struct in6_addr	grec_src[0];
};

struct mld2_report {
	__u8	type;
	__u8	resv1;
	__sum16	csum;
	__be16	resv2;
	__be16	ngrec;
	struct mld2_grec grec[0];
};

struct mld2_query {
	__u8 type;
	__u8 code;
	__sum16 csum;
	__be16 mrc;
	__be16 resv1;
	struct in6_addr mca;
#if defined(__LITTLE_ENDIAN_BITFIELD)
	__u8 qrv:3,
	     suppress:1,
	     resv2:4;
#elif defined(__BIG_ENDIAN_BITFIELD)
	__u8 resv2:4,
	     suppress:1,
	     qrv:3;
#else
#error "Please fix <asm/byteorder.h>"
#endif
	__u8 qqic;
	__be16 nsrcs;
	struct in6_addr srcs[0];
};

static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT;

/* Big mc list lock for all the sockets */
static DEFINE_RWLOCK(ipv6_sk_mc_lock);

static struct socket *igmp6_socket;

int __ipv6_dev_mc_dec(struct inet6_dev *idev, struct in6_addr *addr);

static void igmp6_join_group(struct ifmcaddr6 *ma);
static void igmp6_leave_group(struct ifmcaddr6 *ma);
static void igmp6_timer_handler(unsigned long data);

static void mld_gq_timer_expire(unsigned long data);
static void mld_ifc_timer_expire(unsigned long data);
static void mld_ifc_event(struct inet6_dev *idev);
static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *pmc);
static void mld_del_delrec(struct inet6_dev *idev, struct in6_addr *addr);
static void mld_clear_delrec(struct inet6_dev *idev);
static int sf_setstate(struct ifmcaddr6 *pmc);
static void sf_markstate(struct ifmcaddr6 *pmc);
static void ip6_mc_clear_src(struct ifmcaddr6 *pmc);
static int ip6_mc_del_src(struct inet6_dev *idev, struct in6_addr *pmca,
			  int sfmode, int sfcount, struct in6_addr *psfsrc,
			  int delta);
static int ip6_mc_add_src(struct inet6_dev *idev, struct in6_addr *pmca,
			  int sfmode, int sfcount, struct in6_addr *psfsrc,
			  int delta);
static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
			    struct inet6_dev *idev);


#define IGMP6_UNSOLICITED_IVAL	(10*HZ)
#define MLD_QRV_DEFAULT		2

#define MLD_V1_SEEN(idev) (ipv6_devconf.force_mld_version == 1 || \
		(idev)->cnf.force_mld_version == 1 || \
		((idev)->mc_v1_seen && \
		time_before(jiffies, (idev)->mc_v1_seen)))

#define MLDV2_MASK(value, nb) ((nb)>=32 ? (value) : ((1<<(nb))-1) & (value))
#define MLDV2_EXP(thresh, nbmant, nbexp, value) \
	((value) < (thresh) ? (value) : \
	((MLDV2_MASK(value, nbmant) | (1<<(nbmant))) << \
	(MLDV2_MASK((value) >> (nbmant), nbexp) + (nbexp))))

#define MLDV2_QQIC(value) MLDV2_EXP(0x80, 4, 3, value)
#define MLDV2_MRC(value) MLDV2_EXP(0x8000, 12, 3, value)

#define IPV6_MLD_MAX_MSF	64

int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF;

/*
 *	socket join on multicast group
 */

int ipv6_sock_mc_join(struct sock *sk, int ifindex, struct in6_addr *addr)
{
	struct net_device *dev = NULL;
	struct ipv6_mc_socklist *mc_lst;
	struct ipv6_pinfo *np = inet6_sk(sk);
	int err;

	if (!ipv6_addr_is_multicast(addr))
		return -EINVAL;

	read_lock_bh(&ipv6_sk_mc_lock);
	for (mc_lst=np->ipv6_mc_list; mc_lst; mc_lst=mc_lst->next) {
		if ((ifindex == 0 || mc_lst->ifindex == ifindex) &&
		    ipv6_addr_equal(&mc_lst->addr, addr)) {
			read_unlock_bh(&ipv6_sk_mc_lock);
			return -EADDRINUSE;
		}
	}
	read_unlock_bh(&ipv6_sk_mc_lock);

	mc_lst = sock_kmalloc(sk, sizeof(struct ipv6_mc_socklist), GFP_KERNEL);

	if (mc_lst == NULL)
		return -ENOMEM;

	mc_lst->next = NULL;
	ipv6_addr_copy(&mc_lst->addr, addr);

	if (ifindex == 0) {
		struct rt6_info *rt;
		rt = rt6_lookup(addr, NULL, 0, 0);
		if (rt) {
			dev = rt->rt6i_dev;
			dev_hold(dev);
			dst_release(&rt->u.dst);
		}
	} else
		dev = dev_get_by_index(&init_net, ifindex);

	if (dev == NULL) {
		sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));
		return -ENODEV;
	}

	mc_lst->ifindex = dev->ifindex;
	mc_lst->sfmode = MCAST_EXCLUDE;
	rwlock_init(&mc_lst->sflock);
	mc_lst->sflist = NULL;

	/*
	 *	now add/increase the group membership on the device
	 */

	err = ipv6_dev_mc_inc(dev, addr);

	if (err) {
		sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));
		dev_put(dev);
		return err;
	}

	write_lock_bh(&ipv6_sk_mc_lock);
	mc_lst->next = np->ipv6_mc_list;
	np->ipv6_mc_list = mc_lst;
	write_unlock_bh(&ipv6_sk_mc_lock);

	dev_put(dev);

	return 0;
}

/*
 *	socket leave on multicast group
 */
int ipv6_sock_mc_drop(struct sock *sk, int ifindex, struct in6_addr *addr)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct ipv6_mc_socklist *mc_lst, **lnk;

	write_lock_bh(&ipv6_sk_mc_lock);
	for (lnk = &np->ipv6_mc_list; (mc_lst = *lnk) !=NULL ; lnk = &mc_lst->next) {
		if ((ifindex == 0 || mc_lst->ifindex == ifindex) &&
		    ipv6_addr_equal(&mc_lst->addr, addr)) {
			struct net_device *dev;

			*lnk = mc_lst->next;
			write_unlock_bh(&ipv6_sk_mc_lock);

			if ((dev = dev_get_by_index(&init_net, mc_lst->ifindex)) != NULL) {
				struct inet6_dev *idev = in6_dev_get(dev);

				(void) ip6_mc_leave_src(sk, mc_lst, idev);
				if (idev) {
					__ipv6_dev_mc_dec(idev, &mc_lst->addr);
					in6_dev_put(idev);
				}
				dev_put(dev);
			} else
				(void) ip6_mc_leave_src(sk, mc_lst, NULL);
			sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));
			return 0;
		}
	}
	write_unlock_bh(&ipv6_sk_mc_lock);

	return -EADDRNOTAVAIL;
}

static struct inet6_dev *ip6_mc_find_dev(struct in6_addr *group, int ifindex)
{
	struct net_device *dev = NULL;
	struct inet6_dev *idev = NULL;

	if (ifindex == 0) {
		struct rt6_info *rt;

		rt = rt6_lookup(group, NULL, 0, 0);
		if (rt) {
			dev = rt->rt6i_dev;
			dev_hold(dev);
			dst_release(&rt->u.dst);
		}
	} else
		dev = dev_get_by_index(&init_net, ifindex);

	if (!dev)
		return NULL;
	idev = in6_dev_get(dev);
	if (!idev) {
		dev_put(dev);
		return NULL;
	}
	read_lock_bh(&idev->lock);
	if (idev->dead) {
		read_unlock_bh(&idev->lock);
		in6_dev_put(idev);
		dev_put(dev);
		return NULL;
	}
	return idev;
}

void ipv6_sock_mc_close(struct sock *sk)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct ipv6_mc_socklist *mc_lst;

	write_lock_bh(&ipv6_sk_mc_lock);
	while ((mc_lst = np->ipv6_mc_list) != NULL) {
		struct net_device *dev;

		np->ipv6_mc_list = mc_lst->next;
		write_unlock_bh(&ipv6_sk_mc_lock);

		dev = dev_get_by_index(&init_net, mc_lst->ifindex);
		if (dev) {
			struct inet6_dev *idev = in6_dev_get(dev);

			(void) ip6_mc_leave_src(sk, mc_lst, idev);
			if (idev) {
				__ipv6_dev_mc_dec(idev, &mc_lst->addr);
				in6_dev_put(idev);
			}
			dev_put(dev);
		} else
			(void) ip6_mc_leave_src(sk, mc_lst, NULL);

		sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));

		write_lock_bh(&ipv6_sk_mc_lock);
	}
	write_unlock_bh(&ipv6_sk_mc_lock);
}

int ip6_mc_source(int add, int omode, struct sock *sk,
	struct group_source_req *pgsr)
{
	struct in6_addr *source, *group;
	struct ipv6_mc_socklist *pmc;
	struct net_device *dev;
	struct inet6_dev *idev;
	struct ipv6_pinfo *inet6 = inet6_sk(sk);
	struct ip6_sf_socklist *psl;
	int i, j, rv;
	int leavegroup = 0;
	int pmclocked = 0;
	int err;

	if (pgsr->gsr_group.ss_family != AF_INET6 ||
	    pgsr->gsr_source.ss_family != AF_INET6)
		return -EINVAL;

	source = &((struct sockaddr_in6 *)&pgsr->gsr_source)->sin6_addr;
	group = &((struct sockaddr_in6 *)&pgsr->gsr_group)->sin6_addr;

	if (!ipv6_addr_is_multicast(group))
		return -EINVAL;

	idev = ip6_mc_find_dev(group, pgsr->gsr_interface);
	if (!idev)
		return -ENODEV;
	dev = idev->dev;

	err = -EADDRNOTAVAIL;

	read_lock_bh(&ipv6_sk_mc_lock);
	for (pmc=inet6->ipv6_mc_list; pmc; pmc=pmc->next) {
		if (pgsr->gsr_interface && pmc->ifindex != pgsr->gsr_interface)
			continue;
		if (ipv6_addr_equal(&pmc->addr, group))
			break;
	}
	if (!pmc) {		/* must have a prior join */
		err = -EINVAL;
		goto done;
	}
	/* if a source filter was set, must be the same mode as before */
	if (pmc->sflist) {
		if (pmc->sfmode != omode) {
			err = -EINVAL;
			goto done;
		}
	} else if (pmc->sfmode != omode) {
		/* allow mode switches for empty-set filters */
		ip6_mc_add_src(idev, group, omode, 0, NULL, 0);
		ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0);
		pmc->sfmode = omode;
	}

	write_lock_bh(&pmc->sflock);
	pmclocked = 1;

	psl = pmc->sflist;
	if (!add) {
		if (!psl)
			goto done;	/* err = -EADDRNOTAVAIL */
		rv = !0;
		for (i=0; i<psl->sl_count; i++) {
			rv = memcmp(&psl->sl_addr[i], source,
				sizeof(struct in6_addr));
			if (rv == 0)
				break;
		}
		if (rv)		/* source not found */
			goto done;	/* err = -EADDRNOTAVAIL */

		/* special case - (INCLUDE, empty) == LEAVE_GROUP */
		if (psl->sl_count == 1 && omode == MCAST_INCLUDE) {
			leavegroup = 1;
			goto done;
		}

		/* update the interface filter */
		ip6_mc_del_src(idev, group, omode, 1, source, 1);

		for (j=i+1; j<psl->sl_count; j++)
			psl->sl_addr[j-1] = psl->sl_addr[j];
		psl->sl_count--;
		err = 0;
		goto done;
	}
	/* else, add a new source to the filter */

	if (psl && psl->sl_count >= sysctl_mld_max_msf) {
		err = -ENOBUFS;
		goto done;
	}
	if (!psl || psl->sl_count == psl->sl_max) {
		struct ip6_sf_socklist *newpsl;
		int count = IP6_SFBLOCK;

		if (psl)
			count += psl->sl_max;
		newpsl = sock_kmalloc(sk, IP6_SFLSIZE(count), GFP_ATOMIC);
		if (!newpsl) {
			err = -ENOBUFS;
			goto done;
		}
		newpsl->sl_max = count;
		newpsl->sl_count = count - IP6_SFBLOCK;
		if (psl) {
			for (i=0; i<psl->sl_count; i++)
				newpsl->sl_addr[i] = psl->sl_addr[i];
			sock_kfree_s(sk, psl, IP6_SFLSIZE(psl->sl_max));
		}
		pmc->sflist = psl = newpsl;
	}
	rv = 1;	/* > 0 for insert logic below if sl_count is 0 */
	for (i=0; i<psl->sl_count; i++) {
		rv = memcmp(&psl->sl_addr[i], source, sizeof(struct in6_addr));
		if (rv == 0)
			break;
	}
	if (rv == 0)		/* address already there is an error */
		goto done;
	for (j=psl->sl_count-1; j>=i; j--)
		psl->sl_addr[j+1] = psl->sl_addr[j];
	psl->sl_addr[i] = *source;
	psl->sl_count++;
	err = 0;
	/* update the interface list */
	ip6_mc_add_src(idev, group, omode, 1, source, 1);
done:
	if (pmclocked)
		write_unlock_bh(&pmc->sflock);
	read_unlock_bh(&ipv6_sk_mc_lock);
	read_unlock_bh(&idev->lock);
	in6_dev_put(idev);
	dev_put(dev);
	if (leavegroup)
		return ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group);
	return err;
}

int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf)
{
	struct in6_addr *group;
	struct ipv6_mc_socklist *pmc;
	struct net_device *dev;
	struct inet6_dev *idev;
	struct ipv6_pinfo *inet6 = inet6_sk(sk);
	struct ip6_sf_socklist *newpsl, *psl;
	int leavegroup = 0;
	int i, err;

	group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr;

	if (!ipv6_addr_is_multicast(group))
		return -EINVAL;
	if (gsf->gf_fmode != MCAST_INCLUDE &&
	    gsf->gf_fmode != MCAST_EXCLUDE)
		return -EINVAL;

	idev = ip6_mc_find_dev(group, gsf->gf_interface);

	if (!idev)
		return -ENODEV;
	dev = idev->dev;

	err = 0;
	read_lock_bh(&ipv6_sk_mc_lock);

	if (gsf->gf_fmode == MCAST_INCLUDE && gsf->gf_numsrc == 0) {
		leavegroup = 1;
		goto done;
	}

	for (pmc=inet6->ipv6_mc_list; pmc; pmc=pmc->next) {