dn_table.c

linux 内核源代码

/*
 * DECnet       An implementation of the DECnet protocol suite for the LINUX
 *              operating system.  DECnet is implemented using the  BSD Socket
 *              interface as the means of communication with the user level.
 *
 *              DECnet Routing Forwarding Information Base (Routing Tables)
 *
 * Author:      Steve Whitehouse <[e-mail]>
 *              Mostly copied from the IPv4 routing code
 *
 *
 * Changes:
 *
 */
#include <linux/string.h>
#include <linux/net.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/init.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/netdevice.h>
#include <linux/timer.h>
#include <linux/spinlock.h>
#include <asm/atomic.h>
#include <asm/uaccess.h>
#include <linux/route.h> /* RTF_xxx */
#include <net/neighbour.h>
#include <net/netlink.h>
#include <net/dst.h>
#include <net/flow.h>
#include <net/fib_rules.h>
#include <net/dn.h>
#include <net/dn_route.h>
#include <net/dn_fib.h>
#include <net/dn_neigh.h>
#include <net/dn_dev.h>

struct dn_zone
{
	struct dn_zone		*dz_next;
	struct dn_fib_node 	**dz_hash;
	int			dz_nent;
	int			dz_divisor;
	u32			dz_hashmask;
#define DZ_HASHMASK(dz)	((dz)->dz_hashmask)
	int			dz_order;
	__le16			dz_mask;
#define DZ_MASK(dz)	((dz)->dz_mask)
};

struct dn_hash
{
	struct dn_zone	*dh_zones[17];
	struct dn_zone	*dh_zone_list;
};

#define dz_key_0(key)		((key).datum = 0)
#define dz_prefix(key,dz)	((key).datum)

#define for_nexthops(fi) { int nhsel; const struct dn_fib_nh *nh;\
	for(nhsel = 0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++)

#define endfor_nexthops(fi) }

#define DN_MAX_DIVISOR 1024
#define DN_S_ZOMBIE 1
#define DN_S_ACCESSED 2

#define DN_FIB_SCAN(f, fp) \
for( ; ((f) = *(fp)) != NULL; (fp) = &(f)->fn_next)

#define DN_FIB_SCAN_KEY(f, fp, key) \
for( ; ((f) = *(fp)) != NULL && dn_key_eq((f)->fn_key, (key)); (fp) = &(f)->fn_next)

#define RT_TABLE_MIN 1
#define DN_FIB_TABLE_HASHSZ 256
static struct hlist_head dn_fib_table_hash[DN_FIB_TABLE_HASHSZ];
static DEFINE_RWLOCK(dn_fib_tables_lock);

static struct kmem_cache *dn_hash_kmem __read_mostly;
static int dn_fib_hash_zombies;

static inline dn_fib_idx_t dn_hash(dn_fib_key_t key, struct dn_zone *dz)
{
	u16 h = dn_ntohs(key.datum)>>(16 - dz->dz_order);
	h ^= (h >> 10);
	h ^= (h >> 6);
	h &= DZ_HASHMASK(dz);
	return *(dn_fib_idx_t *)&h;
}

static inline dn_fib_key_t dz_key(__le16 dst, struct dn_zone *dz)
{
	dn_fib_key_t k;
	k.datum = dst & DZ_MASK(dz);
	return k;
}

static inline struct dn_fib_node **dn_chain_p(dn_fib_key_t key, struct dn_zone *dz)
{
	return &dz->dz_hash[dn_hash(key, dz).datum];
}

static inline struct dn_fib_node *dz_chain(dn_fib_key_t key, struct dn_zone *dz)
{
	return dz->dz_hash[dn_hash(key, dz).datum];
}

static inline int dn_key_eq(dn_fib_key_t a, dn_fib_key_t b)
{
	return a.datum == b.datum;
}

static inline int dn_key_leq(dn_fib_key_t a, dn_fib_key_t b)
{
	return a.datum <= b.datum;
}

static inline void dn_rebuild_zone(struct dn_zone *dz,
				   struct dn_fib_node **old_ht,
				   int old_divisor)
{
	int i;
	struct dn_fib_node *f, **fp, *next;

	for(i = 0; i < old_divisor; i++) {
		for(f = old_ht[i]; f; f = f->fn_next) {
			next = f->fn_next;
			for(fp = dn_chain_p(f->fn_key, dz);
				*fp && dn_key_leq((*fp)->fn_key, f->fn_key);
				fp = &(*fp)->fn_next)
				/* NOTHING */;
			f->fn_next = *fp;
			*fp = f;
		}
	}
}

static void dn_rehash_zone(struct dn_zone *dz)
{
	struct dn_fib_node **ht, **old_ht;
	int old_divisor, new_divisor;
	u32 new_hashmask;

	old_divisor = dz->dz_divisor;

	switch(old_divisor) {
		case 16:
			new_divisor = 256;
			new_hashmask = 0xFF;
			break;
		default:
			printk(KERN_DEBUG "DECnet: dn_rehash_zone: BUG! %d\n", old_divisor);
		case 256:
			new_divisor = 1024;
			new_hashmask = 0x3FF;
			break;
	}

	ht = kcalloc(new_divisor, sizeof(struct dn_fib_node*), GFP_KERNEL);
	if (ht == NULL)
		return;

	write_lock_bh(&dn_fib_tables_lock);
	old_ht = dz->dz_hash;
	dz->dz_hash = ht;
	dz->dz_hashmask = new_hashmask;
	dz->dz_divisor = new_divisor;
	dn_rebuild_zone(dz, old_ht, old_divisor);
	write_unlock_bh(&dn_fib_tables_lock);
	kfree(old_ht);
}

static void dn_free_node(struct dn_fib_node *f)
{
	dn_fib_release_info(DN_FIB_INFO(f));
	kmem_cache_free(dn_hash_kmem, f);
}


static struct dn_zone *dn_new_zone(struct dn_hash *table, int z)
{
	int i;
	struct dn_zone *dz = kzalloc(sizeof(struct dn_zone), GFP_KERNEL);
	if (!dz)
		return NULL;

	if (z) {
		dz->dz_divisor = 16;
		dz->dz_hashmask = 0x0F;
	} else {
		dz->dz_divisor = 1;
		dz->dz_hashmask = 0;
	}

	dz->dz_hash = kcalloc(dz->dz_divisor, sizeof(struct dn_fib_node *), GFP_KERNEL);
	if (!dz->dz_hash) {
		kfree(dz);
		return NULL;
	}

	dz->dz_order = z;
	dz->dz_mask = dnet_make_mask(z);

	for(i = z + 1; i <= 16; i++)
		if (table->dh_zones[i])
			break;

	write_lock_bh(&dn_fib_tables_lock);
	if (i>16) {
		dz->dz_next = table->dh_zone_list;
		table->dh_zone_list = dz;
	} else {
		dz->dz_next = table->dh_zones[i]->dz_next;
		table->dh_zones[i]->dz_next = dz;
	}
	table->dh_zones[z] = dz;
	write_unlock_bh(&dn_fib_tables_lock);
	return dz;
}


static int dn_fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct dn_kern_rta *rta, struct dn_fib_info *fi)
{
	struct rtnexthop *nhp;
	int nhlen;

	if (rta->rta_priority && *rta->rta_priority != fi->fib_priority)
		return 1;

	if (rta->rta_oif || rta->rta_gw) {
		if ((!rta->rta_oif || *rta->rta_oif == fi->fib_nh->nh_oif) &&
		    (!rta->rta_gw  || memcmp(rta->rta_gw, &fi->fib_nh->nh_gw, 2) == 0))
			return 0;
		return 1;
	}

	if (rta->rta_mp == NULL)
		return 0;

	nhp = RTA_DATA(rta->rta_mp);
	nhlen = RTA_PAYLOAD(rta->rta_mp);

	for_nexthops(fi) {
		int attrlen = nhlen - sizeof(struct rtnexthop);
		__le16 gw;

		if (attrlen < 0 || (nhlen -= nhp->rtnh_len) < 0)
			return -EINVAL;
		if (nhp->rtnh_ifindex && nhp->rtnh_ifindex != nh->nh_oif)
			return 1;
		if (attrlen) {
			gw = dn_fib_get_attr16(RTNH_DATA(nhp), attrlen, RTA_GATEWAY);

			if (gw && gw != nh->nh_gw)
				return 1;
		}
		nhp = RTNH_NEXT(nhp);
	} endfor_nexthops(fi);

	return 0;
}

static inline size_t dn_fib_nlmsg_size(struct dn_fib_info *fi)
{
	size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg))
			 + nla_total_size(4) /* RTA_TABLE */
			 + nla_total_size(2) /* RTA_DST */
			 + nla_total_size(4); /* RTA_PRIORITY */

	/* space for nested metrics */
	payload += nla_total_size((RTAX_MAX * nla_total_size(4)));

	if (fi->fib_nhs) {
		/* Also handles the special case fib_nhs == 1 */

		/* each nexthop is packed in an attribute */
		size_t nhsize = nla_total_size(sizeof(struct rtnexthop));

		/* may contain a gateway attribute */
		nhsize += nla_total_size(4);

		/* all nexthops are packed in a nested attribute */
		payload += nla_total_size(fi->fib_nhs * nhsize);
	}

	return payload;
}

static int dn_fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
			u32 tb_id, u8 type, u8 scope, void *dst, int dst_len,
			struct dn_fib_info *fi, unsigned int flags)
{
	struct rtmsg *rtm;
	struct nlmsghdr *nlh;
	unsigned char *b = skb_tail_pointer(skb);

	nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*rtm), flags);
	rtm = NLMSG_DATA(nlh);
	rtm->rtm_family = AF_DECnet;
	rtm->rtm_dst_len = dst_len;
	rtm->rtm_src_len = 0;
	rtm->rtm_tos = 0;
	rtm->rtm_table = tb_id;
	RTA_PUT_U32(skb, RTA_TABLE, tb_id);
	rtm->rtm_flags = fi->fib_flags;
	rtm->rtm_scope = scope;
	rtm->rtm_type  = type;
	if (rtm->rtm_dst_len)
		RTA_PUT(skb, RTA_DST, 2, dst);
	rtm->rtm_protocol = fi->fib_protocol;
	if (fi->fib_priority)
		RTA_PUT(skb, RTA_PRIORITY, 4, &fi->fib_priority);
	if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0)
		goto rtattr_failure;
	if (fi->fib_nhs == 1) {
		if (fi->fib_nh->nh_gw)
			RTA_PUT(skb, RTA_GATEWAY, 2, &fi->fib_nh->nh_gw);
		if (fi->fib_nh->nh_oif)
			RTA_PUT(skb, RTA_OIF, sizeof(int), &fi->fib_nh->nh_oif);
	}
	if (fi->fib_nhs > 1) {
		struct rtnexthop *nhp;
		struct rtattr *mp_head;
		if (skb_tailroom(skb) <= RTA_SPACE(0))
			goto rtattr_failure;
		mp_head = (struct rtattr *)skb_put(skb, RTA_SPACE(0));

		for_nexthops(fi) {
			if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4))
				goto rtattr_failure;
			nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp)));
			nhp->rtnh_flags = nh->nh_flags & 0xFF;
			nhp->rtnh_hops = nh->nh_weight - 1;
			nhp->rtnh_ifindex = nh->nh_oif;
			if (nh->nh_gw)
				RTA_PUT(skb, RTA_GATEWAY, 2, &nh->nh_gw);
			nhp->rtnh_len = skb_tail_pointer(skb) - (unsigned char *)nhp;
		} endfor_nexthops(fi);
		mp_head->rta_type = RTA_MULTIPATH;
		mp_head->rta_len = skb_tail_pointer(skb) - (u8 *)mp_head;
	}

	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
	return skb->len;


nlmsg_failure:
rtattr_failure:
	nlmsg_trim(skb, b);
	return -EMSGSIZE;
}


static void dn_rtmsg_fib(int event, struct dn_fib_node *f, int z, u32 tb_id,
			struct nlmsghdr *nlh, struct netlink_skb_parms *req)
{
	struct sk_buff *skb;
	u32 pid = req ? req->pid : 0;
	int err = -ENOBUFS;

	skb = nlmsg_new(dn_fib_nlmsg_size(DN_FIB_INFO(f)), GFP_KERNEL);
	if (skb == NULL)
		goto errout;

	err = dn_fib_dump_info(skb, pid, nlh->nlmsg_seq, event, tb_id,
			       f->fn_type, f->fn_scope, &f->fn_key, z,
			       DN_FIB_INFO(f), 0);
	if (err < 0) {
		/* -EMSGSIZE implies BUG in dn_fib_nlmsg_size() */
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(skb);
		goto errout;
	}
	err = rtnl_notify(skb, pid, RTNLGRP_DECnet_ROUTE, nlh, GFP_KERNEL);
errout:
	if (err < 0)
		rtnl_set_sk_err(RTNLGRP_DECnet_ROUTE, err);
}

static __inline__ int dn_hash_dump_bucket(struct sk_buff *skb,
				struct netlink_callback *cb,
				struct dn_fib_table *tb,
				struct dn_zone *dz,
				struct dn_fib_node *f)
{
	int i, s_i;

	s_i = cb->args[4];
	for(i = 0; f; i++, f = f->fn_next) {
		if (i < s_i)
			continue;
		if (f->fn_state & DN_S_ZOMBIE)
			continue;
		if (dn_fib_dump_info(skb, NETLINK_CB(cb->skb).pid,
				cb->nlh->nlmsg_seq,
				RTM_NEWROUTE,
				tb->n,
				(f->fn_state & DN_S_ZOMBIE) ? 0 : f->fn_type,
				f->fn_scope, &f->fn_key, dz->dz_order,
				f->fn_info, NLM_F_MULTI) < 0) {
			cb->args[4] = i;
			return -1;
		}
	}
	cb->args[4] = i;
	return skb->len;
}

static __inline__ int dn_hash_dump_zone(struct sk_buff *skb,
				struct netlink_callback *cb,
				struct dn_fib_table *tb,
				struct dn_zone *dz)
{
	int h, s_h;

	s_h = cb->args[3];
	for(h = 0; h < dz->dz_divisor; h++) {
		if (h < s_h)
			continue;
		if (h > s_h)
			memset(&cb->args[4], 0, sizeof(cb->args) - 4*sizeof(cb->args[0]));
		if (dz->dz_hash == NULL || dz->dz_hash[h] == NULL)
			continue;
		if (dn_hash_dump_bucket(skb, cb, tb, dz, dz->dz_hash[h]) < 0) {
			cb->args[3] = h;
			return -1;
		}
	}
	cb->args[3] = h;
	return skb->len;
}

static int dn_fib_table_dump(struct dn_fib_table *tb, struct sk_buff *skb,
				struct netlink_callback *cb)
{
	int m, s_m;
	struct dn_zone *dz;
	struct dn_hash *table = (struct dn_hash *)tb->data;

	s_m = cb->args[2];
	read_lock(&dn_fib_tables_lock);
	for(dz = table->dh_zone_list, m = 0; dz; dz = dz->dz_next, m++) {
		if (m < s_m)
			continue;
		if (m > s_m)
			memset(&cb->args[3], 0, sizeof(cb->args) - 3*sizeof(cb->args[0]));

		if (dn_hash_dump_zone(skb, cb, tb, dz) < 0) {