neighbour.c

linux 内核源代码

	read_lock_bh(&tbl->lock);
	ndtmsg->ndtm_family = tbl->family;
	ndtmsg->ndtm_pad1   = 0;
	ndtmsg->ndtm_pad2   = 0;

	NLA_PUT_STRING(skb, NDTA_NAME, tbl->id);
	NLA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval);
	NLA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1);
	NLA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2);
	NLA_PUT_U32(skb, NDTA_THRESH3, tbl->gc_thresh3);

	{
		unsigned long now = jiffies;
		unsigned int flush_delta = now - tbl->last_flush;
		unsigned int rand_delta = now - tbl->last_rand;

		struct ndt_config ndc = {
			.ndtc_key_len		= tbl->key_len,
			.ndtc_entry_size	= tbl->entry_size,
			.ndtc_entries		= atomic_read(&tbl->entries),
			.ndtc_last_flush	= jiffies_to_msecs(flush_delta),
			.ndtc_last_rand		= jiffies_to_msecs(rand_delta),
			.ndtc_hash_rnd		= tbl->hash_rnd,
			.ndtc_hash_mask		= tbl->hash_mask,
			.ndtc_hash_chain_gc	= tbl->hash_chain_gc,
			.ndtc_proxy_qlen	= tbl->proxy_queue.qlen,
		};

		NLA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc);
	}

	{
		int cpu;
		struct ndt_stats ndst;

		memset(&ndst, 0, sizeof(ndst));

		for_each_possible_cpu(cpu) {
			struct neigh_statistics	*st;

			st = per_cpu_ptr(tbl->stats, cpu);
			ndst.ndts_allocs		+= st->allocs;
			ndst.ndts_destroys		+= st->destroys;
			ndst.ndts_hash_grows		+= st->hash_grows;
			ndst.ndts_res_failed		+= st->res_failed;
			ndst.ndts_lookups		+= st->lookups;
			ndst.ndts_hits			+= st->hits;
			ndst.ndts_rcv_probes_mcast	+= st->rcv_probes_mcast;
			ndst.ndts_rcv_probes_ucast	+= st->rcv_probes_ucast;
			ndst.ndts_periodic_gc_runs	+= st->periodic_gc_runs;
			ndst.ndts_forced_gc_runs	+= st->forced_gc_runs;
		}

		NLA_PUT(skb, NDTA_STATS, sizeof(ndst), &ndst);
	}

	BUG_ON(tbl->parms.dev);
	if (neightbl_fill_parms(skb, &tbl->parms) < 0)
		goto nla_put_failure;

	read_unlock_bh(&tbl->lock);
	return nlmsg_end(skb, nlh);

nla_put_failure:
	read_unlock_bh(&tbl->lock);
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
}

static int neightbl_fill_param_info(struct sk_buff *skb,
				    struct neigh_table *tbl,
				    struct neigh_parms *parms,
				    u32 pid, u32 seq, int type,
				    unsigned int flags)
{
	struct ndtmsg *ndtmsg;
	struct nlmsghdr *nlh;

	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndtmsg), flags);
	if (nlh == NULL)
		return -EMSGSIZE;

	ndtmsg = nlmsg_data(nlh);

	read_lock_bh(&tbl->lock);
	ndtmsg->ndtm_family = tbl->family;
	ndtmsg->ndtm_pad1   = 0;
	ndtmsg->ndtm_pad2   = 0;

	if (nla_put_string(skb, NDTA_NAME, tbl->id) < 0 ||
	    neightbl_fill_parms(skb, parms) < 0)
		goto errout;

	read_unlock_bh(&tbl->lock);
	return nlmsg_end(skb, nlh);
errout:
	read_unlock_bh(&tbl->lock);
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
}

static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl,
						      int ifindex)
{
	struct neigh_parms *p;

	for (p = &tbl->parms; p; p = p->next)
		if ((p->dev && p->dev->ifindex == ifindex) ||
		    (!p->dev && !ifindex))
			return p;

	return NULL;
}

static const struct nla_policy nl_neightbl_policy[NDTA_MAX+1] = {
	[NDTA_NAME]		= { .type = NLA_STRING },
	[NDTA_THRESH1]		= { .type = NLA_U32 },
	[NDTA_THRESH2]		= { .type = NLA_U32 },
	[NDTA_THRESH3]		= { .type = NLA_U32 },
	[NDTA_GC_INTERVAL]	= { .type = NLA_U64 },
	[NDTA_PARMS]		= { .type = NLA_NESTED },
};

static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = {
	[NDTPA_IFINDEX]			= { .type = NLA_U32 },
	[NDTPA_QUEUE_LEN]		= { .type = NLA_U32 },
	[NDTPA_PROXY_QLEN]		= { .type = NLA_U32 },
	[NDTPA_APP_PROBES]		= { .type = NLA_U32 },
	[NDTPA_UCAST_PROBES]		= { .type = NLA_U32 },
	[NDTPA_MCAST_PROBES]		= { .type = NLA_U32 },
	[NDTPA_BASE_REACHABLE_TIME]	= { .type = NLA_U64 },
	[NDTPA_GC_STALETIME]		= { .type = NLA_U64 },
	[NDTPA_DELAY_PROBE_TIME]	= { .type = NLA_U64 },
	[NDTPA_RETRANS_TIME]		= { .type = NLA_U64 },
	[NDTPA_ANYCAST_DELAY]		= { .type = NLA_U64 },
	[NDTPA_PROXY_DELAY]		= { .type = NLA_U64 },
	[NDTPA_LOCKTIME]		= { .type = NLA_U64 },
};

static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
	struct neigh_table *tbl;
	struct ndtmsg *ndtmsg;
	struct nlattr *tb[NDTA_MAX+1];
	int err;

	err = nlmsg_parse(nlh, sizeof(*ndtmsg), tb, NDTA_MAX,
			  nl_neightbl_policy);
	if (err < 0)
		goto errout;

	if (tb[NDTA_NAME] == NULL) {
		err = -EINVAL;
		goto errout;
	}

	ndtmsg = nlmsg_data(nlh);
	read_lock(&neigh_tbl_lock);
	for (tbl = neigh_tables; tbl; tbl = tbl->next) {
		if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family)
			continue;

		if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0)
			break;
	}

	if (tbl == NULL) {
		err = -ENOENT;
		goto errout_locked;
	}

	/*
	 * We acquire tbl->lock to be nice to the periodic timers and
	 * make sure they always see a consistent set of values.
	 */
	write_lock_bh(&tbl->lock);

	if (tb[NDTA_PARMS]) {
		struct nlattr *tbp[NDTPA_MAX+1];
		struct neigh_parms *p;
		int i, ifindex = 0;

		err = nla_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS],
				       nl_ntbl_parm_policy);
		if (err < 0)
			goto errout_tbl_lock;

		if (tbp[NDTPA_IFINDEX])
			ifindex = nla_get_u32(tbp[NDTPA_IFINDEX]);

		p = lookup_neigh_params(tbl, ifindex);
		if (p == NULL) {
			err = -ENOENT;
			goto errout_tbl_lock;
		}

		for (i = 1; i <= NDTPA_MAX; i++) {
			if (tbp[i] == NULL)
				continue;

			switch (i) {
			case NDTPA_QUEUE_LEN:
				p->queue_len = nla_get_u32(tbp[i]);
				break;
			case NDTPA_PROXY_QLEN:
				p->proxy_qlen = nla_get_u32(tbp[i]);
				break;
			case NDTPA_APP_PROBES:
				p->app_probes = nla_get_u32(tbp[i]);
				break;
			case NDTPA_UCAST_PROBES:
				p->ucast_probes = nla_get_u32(tbp[i]);
				break;
			case NDTPA_MCAST_PROBES:
				p->mcast_probes = nla_get_u32(tbp[i]);
				break;
			case NDTPA_BASE_REACHABLE_TIME:
				p->base_reachable_time = nla_get_msecs(tbp[i]);
				break;
			case NDTPA_GC_STALETIME:
				p->gc_staletime = nla_get_msecs(tbp[i]);
				break;
			case NDTPA_DELAY_PROBE_TIME:
				p->delay_probe_time = nla_get_msecs(tbp[i]);
				break;
			case NDTPA_RETRANS_TIME:
				p->retrans_time = nla_get_msecs(tbp[i]);
				break;
			case NDTPA_ANYCAST_DELAY:
				p->anycast_delay = nla_get_msecs(tbp[i]);
				break;
			case NDTPA_PROXY_DELAY:
				p->proxy_delay = nla_get_msecs(tbp[i]);
				break;
			case NDTPA_LOCKTIME:
				p->locktime = nla_get_msecs(tbp[i]);
				break;
			}
		}
	}

	if (tb[NDTA_THRESH1])
		tbl->gc_thresh1 = nla_get_u32(tb[NDTA_THRESH1]);

	if (tb[NDTA_THRESH2])
		tbl->gc_thresh2 = nla_get_u32(tb[NDTA_THRESH2]);

	if (tb[NDTA_THRESH3])
		tbl->gc_thresh3 = nla_get_u32(tb[NDTA_THRESH3]);

	if (tb[NDTA_GC_INTERVAL])
		tbl->gc_interval = nla_get_msecs(tb[NDTA_GC_INTERVAL]);

	err = 0;

errout_tbl_lock:
	write_unlock_bh(&tbl->lock);
errout_locked:
	read_unlock(&neigh_tbl_lock);
errout:
	return err;
}

static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
{
	int family, tidx, nidx = 0;
	int tbl_skip = cb->args[0];
	int neigh_skip = cb->args[1];
	struct neigh_table *tbl;

	family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;

	read_lock(&neigh_tbl_lock);
	for (tbl = neigh_tables, tidx = 0; tbl; tbl = tbl->next, tidx++) {
		struct neigh_parms *p;

		if (tidx < tbl_skip || (family && tbl->family != family))
			continue;

		if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).pid,
				       cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL,
				       NLM_F_MULTI) <= 0)
			break;

		for (nidx = 0, p = tbl->parms.next; p; p = p->next, nidx++) {
			if (nidx < neigh_skip)
				continue;

			if (neightbl_fill_param_info(skb, tbl, p,
						     NETLINK_CB(cb->skb).pid,
						     cb->nlh->nlmsg_seq,
						     RTM_NEWNEIGHTBL,
						     NLM_F_MULTI) <= 0)
				goto out;
		}

		neigh_skip = 0;
	}
out:
	read_unlock(&neigh_tbl_lock);
	cb->args[0] = tidx;
	cb->args[1] = nidx;

	return skb->len;
}

static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh,
			   u32 pid, u32 seq, int type, unsigned int flags)
{
	unsigned long now = jiffies;
	struct nda_cacheinfo ci;
	struct nlmsghdr *nlh;
	struct ndmsg *ndm;

	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags);
	if (nlh == NULL)
		return -EMSGSIZE;

	ndm = nlmsg_data(nlh);
	ndm->ndm_family	 = neigh->ops->family;
	ndm->ndm_pad1    = 0;
	ndm->ndm_pad2    = 0;
	ndm->ndm_flags	 = neigh->flags;
	ndm->ndm_type	 = neigh->type;
	ndm->ndm_ifindex = neigh->dev->ifindex;

	NLA_PUT(skb, NDA_DST, neigh->tbl->key_len, neigh->primary_key);

	read_lock_bh(&neigh->lock);
	ndm->ndm_state	 = neigh->nud_state;
	if ((neigh->nud_state & NUD_VALID) &&
	    nla_put(skb, NDA_LLADDR, neigh->dev->addr_len, neigh->ha) < 0) {
		read_unlock_bh(&neigh->lock);
		goto nla_put_failure;
	}

	ci.ndm_used	 = now - neigh->used;
	ci.ndm_confirmed = now - neigh->confirmed;
	ci.ndm_updated	 = now - neigh->updated;
	ci.ndm_refcnt	 = atomic_read(&neigh->refcnt) - 1;
	read_unlock_bh(&neigh->lock);

	NLA_PUT_U32(skb, NDA_PROBES, atomic_read(&neigh->probes));
	NLA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci);

	return nlmsg_end(skb, nlh);

nla_put_failure:
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
}

static void neigh_update_notify(struct neighbour *neigh)
{
	call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh);
	__neigh_notify(neigh, RTM_NEWNEIGH, 0);
}

static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
			    struct netlink_callback *cb)
{
	struct neighbour *n;
	int rc, h, s_h = cb->args[1];
	int idx, s_idx = idx = cb->args[2];

	read_lock_bh(&tbl->lock);
	for (h = 0; h <= tbl->hash_mask; h++) {
		if (h < s_h)
			continue;
		if (h > s_h)
			s_idx = 0;
		for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next, idx++) {
			if (idx < s_idx)
				continue;
			if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid,
					    cb->nlh->nlmsg_seq,
					    RTM_NEWNEIGH,
					    NLM_F_MULTI) <= 0) {
				read_unlock_bh(&tbl->lock);
				rc = -1;
				goto out;
			}
		}
	}
	read_unlock_bh(&tbl->lock);
	rc = skb->len;
out:
	cb->args[1] = h;
	cb->args[2] = idx;
	return rc;
}

static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct neigh_table *tbl;
	int t, family, s_t;

	read_lock(&neigh_tbl_lock);
	family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;
	s_t = cb->args[0];

	for (tbl = neigh_tables, t = 0; tbl; tbl = tbl->next, t++) {
		if (t < s_t || (family && tbl->family != family))
			continue;
		if (t > s_t)
			memset(&cb->args[1], 0, sizeof(cb->args) -
						sizeof(cb->args[0]));
		if (neigh_dump_table(tbl, skb, cb) < 0)
			break;
	}
	read_unlock(&neigh_tbl_lock);

	cb->args[0] = t;
	return skb->len;
}

void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie)
{
	int chain;

	read_lock_bh(&tbl->lock);
	for (chain = 0; chain <= tbl->hash_mask; chain++) {
		struct neighbour *n;

		for (n = tbl->hash_buckets[chain]; n; n = n->next)
			cb(n, cookie);
	}
	read_unlock_bh(&tbl->lock);
}
EXPORT_SYMBOL(neigh_for_each);

/* The tbl->lock must be held as a writer and BH disabled. */
void __neigh_for_each_release(struct neigh_table *tbl,
			      int (*cb)(struct neighbour *))
{
	int chain;

	for (chain = 0; chain <= tbl->hash_mask; chain++) {
		struct neighbour *n, **np;

		np = &tbl->hash_buckets[chain];
		while ((n = *np) != NULL) {
			int release;

			write_lock(&n->lock);
			release = cb(n);
			if (release) {
				*np = n->next;
				n->dead = 1;
			} else
				np = &n->next;
			write_unlock(&n->lock);
			if (release)
				neigh_cleanup_and_release(n);
		}
	}
}
EXPORT_SYMBOL(__neigh_for_each_release);

#ifdef CONFIG_PROC_FS

static struct neighbour *neigh_get_first(struct seq_file *seq)
{
	struct neigh_seq_state *state = seq->private;
	struct neigh_table *tbl = state->tbl;
	struct neighbour *n = NULL;
	int bucket = state->bucket;

	state->flags &= ~NEIGH_SEQ_IS_PNEIGH;
	for (bucket = 0; bucket <= tbl->hash_mask; bucket++) {
		n = tbl->hash_buckets[bucket];

		while (n) {
			if (state->neigh_sub_iter) {
				loff_t fakep = 0;
				void *v;

				v = state->neigh_sub_iter(state, n, &fakep);
				if (!v)
					goto next;
			}
			if (!(state->flags & NEIGH_SEQ_SKIP_NOARP))
				break;
			if (n->nud_state & ~NUD_NOARP)
				break;
		next:
			n = n->next;
		}

		if (n)
			break;
	}
	state->bucket = bucket;

	return n;
}

static struct neighbour *neigh_get_next(struct seq_file *seq,
					struct neighbour *n,
					loff_t *pos)
{
	struct neigh_seq_state *state = seq->private;
	struct neigh_table *tbl = state->tbl;

	if (state->neigh_sub_iter) {
		void *v = state->neigh_sub_iter(state, n, pos);
		if (v)
			return n;
	}
	n = n->next;

	while (1) {
		while (n) {
			if (state->neigh_sub_iter) {
				void *v = state->neigh_sub_iter(state, n, pos);
				if (v)
					return n;
				goto next;
			}
			if (!(state->flags & NEIGH_SEQ_SKIP_NOARP))
				break;

			if (n->nud_state & ~NUD_NOARP)
				break;
		next:
			n = n->next;
		}

		if (n)
			break;

		if (++state->bucket > tbl->hash_mask)
			break;

		n = tbl->hash_buckets[state->bucket];
	}

	if (n && pos)
		--(*pos);
	return n;
}

static struct neighbour *neigh_get_idx(struct seq_file *seq, loff_t *pos)
{
	struct neighbour *n = neigh_get_first(seq);

	if (n) {
		while (*pos) {
			n = neigh_get_next(seq, n, pos);
			if (!n)
				break;
		}