fib_semantics.c

linux 内核源代码

		return kmalloc(bytes, GFP_KERNEL);
	else
		return (struct hlist_head *)
			__get_free_pages(GFP_KERNEL, get_order(bytes));
}

static void fib_hash_free(struct hlist_head *hash, int bytes)
{
	if (!hash)
		return;

	if (bytes <= PAGE_SIZE)
		kfree(hash);
	else
		free_pages((unsigned long) hash, get_order(bytes));
}

static void fib_hash_move(struct hlist_head *new_info_hash,
			  struct hlist_head *new_laddrhash,
			  unsigned int new_size)
{
	struct hlist_head *old_info_hash, *old_laddrhash;
	unsigned int old_size = fib_hash_size;
	unsigned int i, bytes;

	spin_lock_bh(&fib_info_lock);
	old_info_hash = fib_info_hash;
	old_laddrhash = fib_info_laddrhash;
	fib_hash_size = new_size;

	for (i = 0; i < old_size; i++) {
		struct hlist_head *head = &fib_info_hash[i];
		struct hlist_node *node, *n;
		struct fib_info *fi;

		hlist_for_each_entry_safe(fi, node, n, head, fib_hash) {
			struct hlist_head *dest;
			unsigned int new_hash;

			hlist_del(&fi->fib_hash);

			new_hash = fib_info_hashfn(fi);
			dest = &new_info_hash[new_hash];
			hlist_add_head(&fi->fib_hash, dest);
		}
	}
	fib_info_hash = new_info_hash;

	for (i = 0; i < old_size; i++) {
		struct hlist_head *lhead = &fib_info_laddrhash[i];
		struct hlist_node *node, *n;
		struct fib_info *fi;

		hlist_for_each_entry_safe(fi, node, n, lhead, fib_lhash) {
			struct hlist_head *ldest;
			unsigned int new_hash;

			hlist_del(&fi->fib_lhash);

			new_hash = fib_laddr_hashfn(fi->fib_prefsrc);
			ldest = &new_laddrhash[new_hash];
			hlist_add_head(&fi->fib_lhash, ldest);
		}
	}
	fib_info_laddrhash = new_laddrhash;

	spin_unlock_bh(&fib_info_lock);

	bytes = old_size * sizeof(struct hlist_head *);
	fib_hash_free(old_info_hash, bytes);
	fib_hash_free(old_laddrhash, bytes);
}

struct fib_info *fib_create_info(struct fib_config *cfg)
{
	int err;
	struct fib_info *fi = NULL;
	struct fib_info *ofi;
	int nhs = 1;

	/* Fast check to catch the most weird cases */
	if (fib_props[cfg->fc_type].scope > cfg->fc_scope)
		goto err_inval;

#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (cfg->fc_mp) {
		nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len);
		if (nhs == 0)
			goto err_inval;
	}
#endif

	err = -ENOBUFS;
	if (fib_info_cnt >= fib_hash_size) {
		unsigned int new_size = fib_hash_size << 1;
		struct hlist_head *new_info_hash;
		struct hlist_head *new_laddrhash;
		unsigned int bytes;

		if (!new_size)
			new_size = 1;
		bytes = new_size * sizeof(struct hlist_head *);
		new_info_hash = fib_hash_alloc(bytes);
		new_laddrhash = fib_hash_alloc(bytes);
		if (!new_info_hash || !new_laddrhash) {
			fib_hash_free(new_info_hash, bytes);
			fib_hash_free(new_laddrhash, bytes);
		} else {
			memset(new_info_hash, 0, bytes);
			memset(new_laddrhash, 0, bytes);

			fib_hash_move(new_info_hash, new_laddrhash, new_size);
		}

		if (!fib_hash_size)
			goto failure;
	}

	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
	if (fi == NULL)
		goto failure;
	fib_info_cnt++;

	fi->fib_protocol = cfg->fc_protocol;
	fi->fib_flags = cfg->fc_flags;
	fi->fib_priority = cfg->fc_priority;
	fi->fib_prefsrc = cfg->fc_prefsrc;

	fi->fib_nhs = nhs;
	change_nexthops(fi) {
		nh->nh_parent = fi;
	} endfor_nexthops(fi)

	if (cfg->fc_mx) {
		struct nlattr *nla;
		int remaining;

		nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
			int type = nla_type(nla);

			if (type) {
				if (type > RTAX_MAX)
					goto err_inval;
				fi->fib_metrics[type - 1] = nla_get_u32(nla);
			}
		}
	}

	if (cfg->fc_mp) {
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg);
		if (err != 0)
			goto failure;
		if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif)
			goto err_inval;
		if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw)
			goto err_inval;
#ifdef CONFIG_NET_CLS_ROUTE
		if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow)
			goto err_inval;
#endif
#else
		goto err_inval;
#endif
	} else {
		struct fib_nh *nh = fi->fib_nh;

		nh->nh_oif = cfg->fc_oif;
		nh->nh_gw = cfg->fc_gw;
		nh->nh_flags = cfg->fc_flags;
#ifdef CONFIG_NET_CLS_ROUTE
		nh->nh_tclassid = cfg->fc_flow;
#endif
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		nh->nh_weight = 1;
#endif
	}

	if (fib_props[cfg->fc_type].error) {
		if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp)
			goto err_inval;
		goto link_it;
	}

	if (cfg->fc_scope > RT_SCOPE_HOST)
		goto err_inval;

	if (cfg->fc_scope == RT_SCOPE_HOST) {
		struct fib_nh *nh = fi->fib_nh;

		/* Local address is added. */
		if (nhs != 1 || nh->nh_gw)
			goto err_inval;
		nh->nh_scope = RT_SCOPE_NOWHERE;
		nh->nh_dev = dev_get_by_index(&init_net, fi->fib_nh->nh_oif);
		err = -ENODEV;
		if (nh->nh_dev == NULL)
			goto failure;
	} else {
		change_nexthops(fi) {
			if ((err = fib_check_nh(cfg, fi, nh)) != 0)
				goto failure;
		} endfor_nexthops(fi)
	}

	if (fi->fib_prefsrc) {
		if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst ||
		    fi->fib_prefsrc != cfg->fc_dst)
			if (inet_addr_type(fi->fib_prefsrc) != RTN_LOCAL)
				goto err_inval;
	}

link_it:
	if ((ofi = fib_find_info(fi)) != NULL) {
		fi->fib_dead = 1;
		free_fib_info(fi);
		ofi->fib_treeref++;
		return ofi;
	}

	fi->fib_treeref++;
	atomic_inc(&fi->fib_clntref);
	spin_lock_bh(&fib_info_lock);
	hlist_add_head(&fi->fib_hash,
		       &fib_info_hash[fib_info_hashfn(fi)]);
	if (fi->fib_prefsrc) {
		struct hlist_head *head;

		head = &fib_info_laddrhash[fib_laddr_hashfn(fi->fib_prefsrc)];
		hlist_add_head(&fi->fib_lhash, head);
	}
	change_nexthops(fi) {
		struct hlist_head *head;
		unsigned int hash;

		if (!nh->nh_dev)
			continue;
		hash = fib_devindex_hashfn(nh->nh_dev->ifindex);
		head = &fib_info_devhash[hash];
		hlist_add_head(&nh->nh_hash, head);
	} endfor_nexthops(fi)
	spin_unlock_bh(&fib_info_lock);
	return fi;

err_inval:
	err = -EINVAL;

failure:
	if (fi) {
		fi->fib_dead = 1;
		free_fib_info(fi);
	}

	return ERR_PTR(err);
}

/* Note! fib_semantic_match intentionally uses  RCU list functions. */
int fib_semantic_match(struct list_head *head, const struct flowi *flp,
		       struct fib_result *res, __be32 zone, __be32 mask,
			int prefixlen)
{
	struct fib_alias *fa;
	int nh_sel = 0;

	list_for_each_entry_rcu(fa, head, fa_list) {
		int err;

		if (fa->fa_tos &&
		    fa->fa_tos != flp->fl4_tos)
			continue;

		if (fa->fa_scope < flp->fl4_scope)
			continue;

		fa->fa_state |= FA_S_ACCESSED;

		err = fib_props[fa->fa_type].error;
		if (err == 0) {
			struct fib_info *fi = fa->fa_info;

			if (fi->fib_flags & RTNH_F_DEAD)
				continue;

			switch (fa->fa_type) {
			case RTN_UNICAST:
			case RTN_LOCAL:
			case RTN_BROADCAST:
			case RTN_ANYCAST:
			case RTN_MULTICAST:
				for_nexthops(fi) {
					if (nh->nh_flags&RTNH_F_DEAD)
						continue;
					if (!flp->oif || flp->oif == nh->nh_oif)
						break;
				}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
				if (nhsel < fi->fib_nhs) {
					nh_sel = nhsel;
					goto out_fill_res;
				}
#else
				if (nhsel < 1) {
					goto out_fill_res;
				}
#endif
				endfor_nexthops(fi);
				continue;

			default:
				printk(KERN_DEBUG "impossible 102\n");
				return -EINVAL;
			}
		}
		return err;
	}
	return 1;

out_fill_res:
	res->prefixlen = prefixlen;
	res->nh_sel = nh_sel;
	res->type = fa->fa_type;
	res->scope = fa->fa_scope;
	res->fi = fa->fa_info;
	atomic_inc(&res->fi->fib_clntref);
	return 0;
}

/* Find appropriate source address to this destination */

__be32 __fib_res_prefsrc(struct fib_result *res)
{
	return inet_select_addr(FIB_RES_DEV(*res), FIB_RES_GW(*res), res->scope);
}

int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
		  u32 tb_id, u8 type, u8 scope, __be32 dst, int dst_len, u8 tos,
		  struct fib_info *fi, unsigned int flags)
{
	struct nlmsghdr *nlh;
	struct rtmsg *rtm;

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

	rtm = nlmsg_data(nlh);
	rtm->rtm_family = AF_INET;
	rtm->rtm_dst_len = dst_len;
	rtm->rtm_src_len = 0;
	rtm->rtm_tos = tos;
	rtm->rtm_table = tb_id;
	NLA_PUT_U32(skb, RTA_TABLE, tb_id);
	rtm->rtm_type = type;
	rtm->rtm_flags = fi->fib_flags;
	rtm->rtm_scope = scope;
	rtm->rtm_protocol = fi->fib_protocol;

	if (rtm->rtm_dst_len)
		NLA_PUT_BE32(skb, RTA_DST, dst);

	if (fi->fib_priority)
		NLA_PUT_U32(skb, RTA_PRIORITY, fi->fib_priority);

	if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0)
		goto nla_put_failure;

	if (fi->fib_prefsrc)
		NLA_PUT_BE32(skb, RTA_PREFSRC, fi->fib_prefsrc);

	if (fi->fib_nhs == 1) {
		if (fi->fib_nh->nh_gw)
			NLA_PUT_BE32(skb, RTA_GATEWAY, fi->fib_nh->nh_gw);

		if (fi->fib_nh->nh_oif)
			NLA_PUT_U32(skb, RTA_OIF, fi->fib_nh->nh_oif);
#ifdef CONFIG_NET_CLS_ROUTE
		if (fi->fib_nh[0].nh_tclassid)
			NLA_PUT_U32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid);
#endif
	}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (fi->fib_nhs > 1) {
		struct rtnexthop *rtnh;
		struct nlattr *mp;

		mp = nla_nest_start(skb, RTA_MULTIPATH);
		if (mp == NULL)
			goto nla_put_failure;

		for_nexthops(fi) {
			rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
			if (rtnh == NULL)
				goto nla_put_failure;

			rtnh->rtnh_flags = nh->nh_flags & 0xFF;
			rtnh->rtnh_hops = nh->nh_weight - 1;
			rtnh->rtnh_ifindex = nh->nh_oif;

			if (nh->nh_gw)
				NLA_PUT_BE32(skb, RTA_GATEWAY, nh->nh_gw);
#ifdef CONFIG_NET_CLS_ROUTE
			if (nh->nh_tclassid)
				NLA_PUT_U32(skb, RTA_FLOW, nh->nh_tclassid);
#endif
			/* length of rtnetlink header + attributes */
			rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh;
		} endfor_nexthops(fi);

		nla_nest_end(skb, mp);
	}
#endif
	return nlmsg_end(skb, nlh);

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

/*
   Update FIB if:
   - local address disappeared -> we must delete all the entries
     referring to it.
   - device went down -> we must shutdown all nexthops going via it.
 */

int fib_sync_down(__be32 local, struct net_device *dev, int force)
{
	int ret = 0;
	int scope = RT_SCOPE_NOWHERE;

	if (force)
		scope = -1;

	if (local && fib_info_laddrhash) {
		unsigned int hash = fib_laddr_hashfn(local);
		struct hlist_head *head = &fib_info_laddrhash[hash];
		struct hlist_node *node;
		struct fib_info *fi;

		hlist_for_each_entry(fi, node, head, fib_lhash) {
			if (fi->fib_prefsrc == local) {
				fi->fib_flags |= RTNH_F_DEAD;
				ret++;
			}
		}
	}

	if (dev) {
		struct fib_info *prev_fi = NULL;
		unsigned int hash = fib_devindex_hashfn(dev->ifindex);
		struct hlist_head *head = &fib_info_devhash[hash];
		struct hlist_node *node;
		struct fib_nh *nh;

		hlist_for_each_entry(nh, node, head, nh_hash) {
			struct fib_info *fi = nh->nh_parent;
			int dead;

			BUG_ON(!fi->fib_nhs);
			if (nh->nh_dev != dev || fi == prev_fi)
				continue;
			prev_fi = fi;
			dead = 0;
			change_nexthops(fi) {
				if (nh->nh_flags&RTNH_F_DEAD)
					dead++;
				else if (nh->nh_dev == dev &&
					 nh->nh_scope != scope) {
					nh->nh_flags |= RTNH_F_DEAD;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
					spin_lock_bh(&fib_multipath_lock);
					fi->fib_power -= nh->nh_power;
					nh->nh_power = 0;
					spin_unlock_bh(&fib_multipath_lock);
#endif
					dead++;
				}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
				if (force > 1 && nh->nh_dev == dev) {
					dead = fi->fib_nhs;
					break;
				}
#endif
			} endfor_nexthops(fi)
			if (dead == fi->fib_nhs) {
				fi->fib_flags |= RTNH_F_DEAD;
				ret++;
			}
		}
	}

	return ret;
}

#ifdef CONFIG_IP_ROUTE_MULTIPATH

/*
   Dead device goes up. We wake up dead nexthops.
   It takes sense only on multipath routes.
 */

int fib_sync_up(struct net_device *dev)
{
	struct fib_info *prev_fi;
	unsigned int hash;
	struct hlist_head *head;
	struct hlist_node *node;
	struct fib_nh *nh;
	int ret;

	if (!(dev->flags&IFF_UP))
		return 0;

	prev_fi = NULL;
	hash = fib_devindex_hashfn(dev->ifindex);
	head = &fib_info_devhash[hash];
	ret = 0;

	hlist_for_each_entry(nh, node, head, nh_hash) {
		struct fib_info *fi = nh->nh_parent;
		int alive;

		BUG_ON(!fi->fib_nhs);
		if (nh->nh_dev != dev || fi == prev_fi)
			continue;

		prev_fi = fi;
		alive = 0;
		change_nexthops(fi) {
			if (!(nh->nh_flags&RTNH_F_DEAD)) {
				alive++;
				continue;
			}
			if (nh->nh_dev == NULL || !(nh->nh_dev->flags&IFF_UP))
				continue;
			if (nh->nh_dev != dev || !__in_dev_get_rtnl(dev))
				continue;
			alive++;
			spin_lock_bh(&fib_multipath_lock);
			nh->nh_power = 0;
			nh->nh_flags &= ~RTNH_F_DEAD;
			spin_unlock_bh(&fib_multipath_lock);
		} endfor_nexthops(fi)

		if (alive > 0) {
			fi->fib_flags &= ~RTNH_F_DEAD;
			ret++;
		}
	}

	return ret;
}

/*
   The algorithm is suboptimal, but it provides really
   fair weighted route distribution.
 */

void fib_select_multipath(const struct flowi *flp, struct fib_result *res)
{
	struct fib_info *fi = res->fi;
	int w;

	spin_lock_bh(&fib_multipath_lock);
	if (fi->fib_power <= 0) {
		int power = 0;
		change_nexthops(fi) {
			if (!(nh->nh_flags&RTNH_F_DEAD)) {
				power += nh->nh_weight;
				nh->nh_power = nh->nh_weight;
			}
		} endfor_nexthops(fi);
		fi->fib_power = power;
		if (power <= 0) {
			spin_unlock_bh(&fib_multipath_lock);
			/* Race condition: route has just become dead. */
			res->nh_sel = 0;
			return;
		}
	}


	/* w should be random number [0..fi->fib_power-1],
	   it is pretty bad approximation.
	 */

	w = jiffies % fi->fib_power;

	change_nexthops(fi) {
		if (!(nh->nh_flags&RTNH_F_DEAD) && nh->nh_power) {
			if ((w -= nh->nh_power) <= 0) {
				nh->nh_power--;
				fi->fib_power--;
				res->nh_sel = nhsel;
				spin_unlock_bh(&fib_multipath_lock);
				return;
			}
		}
	} endfor_nexthops(fi);

	/* Race condition: route has just become dead. */
	res->nh_sel = 0;
	spin_unlock_bh(&fib_multipath_lock);
}
#endif