fib_semantics.c

Linux Kernel 2.6.9 for OMAP1710

	fi = kmalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
	if (fi == NULL)
		goto failure;
	fib_info_cnt++;
	memset(fi, 0, sizeof(*fi)+nhs*sizeof(struct fib_nh));

	fi->fib_protocol = r->rtm_protocol;

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

	fi->fib_flags = r->rtm_flags;
	if (rta->rta_priority)
		fi->fib_priority = *rta->rta_priority;
	if (rta->rta_mx) {
		int attrlen = RTA_PAYLOAD(rta->rta_mx);
		struct rtattr *attr = RTA_DATA(rta->rta_mx);

		while (RTA_OK(attr, attrlen)) {
			unsigned flavor = attr->rta_type;
			if (flavor) {
				if (flavor > RTAX_MAX)
					goto err_inval;
				fi->fib_metrics[flavor-1] = *(unsigned*)RTA_DATA(attr);
			}
			attr = RTA_NEXT(attr, attrlen);
		}
	}
	if (rta->rta_prefsrc)
		memcpy(&fi->fib_prefsrc, rta->rta_prefsrc, 4);

	if (rta->rta_mp) {
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		if ((err = fib_get_nhs(fi, rta->rta_mp, r)) != 0)
			goto failure;
		if (rta->rta_oif && fi->fib_nh->nh_oif != *rta->rta_oif)
			goto err_inval;
		if (rta->rta_gw && memcmp(&fi->fib_nh->nh_gw, rta->rta_gw, 4))
			goto err_inval;
#ifdef CONFIG_NET_CLS_ROUTE
		if (rta->rta_flow && memcmp(&fi->fib_nh->nh_tclassid, rta->rta_flow, 4))
			goto err_inval;
#endif
#else
		goto err_inval;
#endif
	} else {
		struct fib_nh *nh = fi->fib_nh;
		if (rta->rta_oif)
			nh->nh_oif = *rta->rta_oif;
		if (rta->rta_gw)
			memcpy(&nh->nh_gw, rta->rta_gw, 4);
#ifdef CONFIG_NET_CLS_ROUTE
		if (rta->rta_flow)
			memcpy(&nh->nh_tclassid, rta->rta_flow, 4);
#endif
		nh->nh_flags = r->rtm_flags;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		nh->nh_weight = 1;
#endif
	}

	if (fib_props[r->rtm_type].error) {
		if (rta->rta_gw || rta->rta_oif || rta->rta_mp)
			goto err_inval;
		goto link_it;
	}

	if (r->rtm_scope > RT_SCOPE_HOST)
		goto err_inval;

	if (r->rtm_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(fi->fib_nh->nh_oif);
		err = -ENODEV;
		if (nh->nh_dev == NULL)
			goto failure;
	} else {
		change_nexthops(fi) {
			if ((err = fib_check_nh(r, fi, nh)) != 0)
				goto failure;
		} endfor_nexthops(fi)
	}

	if (fi->fib_prefsrc) {
		if (r->rtm_type != RTN_LOCAL || rta->rta_dst == NULL ||
		    memcmp(&fi->fib_prefsrc, rta->rta_dst, 4))
			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);
	write_lock(&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)
	write_unlock(&fib_info_lock);
	return fi;

err_inval:
	err = -EINVAL;

failure:
        *errp = err;
        if (fi) {
		fi->fib_dead = 1;
		free_fib_info(fi);
	}
	return NULL;
}

int fib_semantic_match(struct list_head *head, const struct flowi *flp,
		       struct fib_result *res, int prefixlen)
{
	struct fib_alias *fa;
	int nh_sel = 0;

	list_for_each_entry(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 */

u32 __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,
	      u8 tb_id, u8 type, u8 scope, void *dst, int dst_len, u8 tos,
	      struct fib_info *fi)
{
	struct rtmsg *rtm;
	struct nlmsghdr  *nlh;
	unsigned char	 *b = skb->tail;

	nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*rtm));
	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;
	rtm->rtm_type = type;
	rtm->rtm_flags = fi->fib_flags;
	rtm->rtm_scope = scope;
	if (rtm->rtm_dst_len)
		RTA_PUT(skb, RTA_DST, 4, dst);
	rtm->rtm_protocol = fi->fib_protocol;
	if (fi->fib_priority)
		RTA_PUT(skb, RTA_PRIORITY, 4, &fi->fib_priority);
#ifdef CONFIG_NET_CLS_ROUTE
	if (fi->fib_nh[0].nh_tclassid)
		RTA_PUT(skb, RTA_FLOW, 4, &fi->fib_nh[0].nh_tclassid);
#endif
	if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0)
		goto rtattr_failure;
	if (fi->fib_prefsrc)
		RTA_PUT(skb, RTA_PREFSRC, 4, &fi->fib_prefsrc);
	if (fi->fib_nhs == 1) {
		if (fi->fib_nh->nh_gw)
			RTA_PUT(skb, RTA_GATEWAY, 4, &fi->fib_nh->nh_gw);
		if (fi->fib_nh->nh_oif)
			RTA_PUT(skb, RTA_OIF, sizeof(int), &fi->fib_nh->nh_oif);
	}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
	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, 4, &nh->nh_gw);
			nhp->rtnh_len = skb->tail - (unsigned char*)nhp;
		} endfor_nexthops(fi);
		mp_head->rta_type = RTA_MULTIPATH;
		mp_head->rta_len = skb->tail - (u8*)mp_head;
	}
#endif
	nlh->nlmsg_len = skb->tail - b;
	return skb->len;

nlmsg_failure:
rtattr_failure:
	skb_trim(skb, b - skb->data);
	return -1;
}

#ifndef CONFIG_IP_NOSIOCRT

int
fib_convert_rtentry(int cmd, struct nlmsghdr *nl, struct rtmsg *rtm,
		    struct kern_rta *rta, struct rtentry *r)
{
	int    plen;
	u32    *ptr;

	memset(rtm, 0, sizeof(*rtm));
	memset(rta, 0, sizeof(*rta));

	if (r->rt_dst.sa_family != AF_INET)
		return -EAFNOSUPPORT;

	/* Check mask for validity:
	   a) it must be contiguous.
	   b) destination must have all host bits clear.
	   c) if application forgot to set correct family (AF_INET),
	      reject request unless it is absolutely clear i.e.
	      both family and mask are zero.
	 */
	plen = 32;
	ptr = &((struct sockaddr_in*)&r->rt_dst)->sin_addr.s_addr;
	if (!(r->rt_flags&RTF_HOST)) {
		u32 mask = ((struct sockaddr_in*)&r->rt_genmask)->sin_addr.s_addr;
		if (r->rt_genmask.sa_family != AF_INET) {
			if (mask || r->rt_genmask.sa_family)
				return -EAFNOSUPPORT;
		}
		if (bad_mask(mask, *ptr))
			return -EINVAL;
		plen = inet_mask_len(mask);
	}

	nl->nlmsg_flags = NLM_F_REQUEST;
	nl->nlmsg_pid = 0;
	nl->nlmsg_seq = 0;
	nl->nlmsg_len = NLMSG_LENGTH(sizeof(*rtm));
	if (cmd == SIOCDELRT) {
		nl->nlmsg_type = RTM_DELROUTE;
		nl->nlmsg_flags = 0;
	} else {
		nl->nlmsg_type = RTM_NEWROUTE;
		nl->nlmsg_flags = NLM_F_REQUEST|NLM_F_CREATE;
		rtm->rtm_protocol = RTPROT_BOOT;
	}

	rtm->rtm_dst_len = plen;
	rta->rta_dst = ptr;

	if (r->rt_metric) {
		*(u32*)&r->rt_pad3 = r->rt_metric - 1;
		rta->rta_priority = (u32*)&r->rt_pad3;
	}
	if (r->rt_flags&RTF_REJECT) {
		rtm->rtm_scope = RT_SCOPE_HOST;
		rtm->rtm_type = RTN_UNREACHABLE;
		return 0;
	}
	rtm->rtm_scope = RT_SCOPE_NOWHERE;
	rtm->rtm_type = RTN_UNICAST;

	if (r->rt_dev) {
		char *colon;
		struct net_device *dev;
		char   devname[IFNAMSIZ];

		if (copy_from_user(devname, r->rt_dev, IFNAMSIZ-1))
			return -EFAULT;
		devname[IFNAMSIZ-1] = 0;
		colon = strchr(devname, ':');
		if (colon)
			*colon = 0;
		dev = __dev_get_by_name(devname);
		if (!dev)
			return -ENODEV;
		rta->rta_oif = &dev->ifindex;
		if (colon) {
			struct in_ifaddr *ifa;
			struct in_device *in_dev = __in_dev_get(dev);
			if (!in_dev)
				return -ENODEV;
			*colon = ':';
			for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next)
				if (strcmp(ifa->ifa_label, devname) == 0)
					break;
			if (ifa == NULL)
				return -ENODEV;
			rta->rta_prefsrc = &ifa->ifa_local;
		}
	}

	ptr = &((struct sockaddr_in*)&r->rt_gateway)->sin_addr.s_addr;
	if (r->rt_gateway.sa_family == AF_INET && *ptr) {
		rta->rta_gw = ptr;
		if (r->rt_flags&RTF_GATEWAY && inet_addr_type(*ptr) == RTN_UNICAST)
			rtm->rtm_scope = RT_SCOPE_UNIVERSE;
	}

	if (cmd == SIOCDELRT)
		return 0;

	if (r->rt_flags&RTF_GATEWAY && rta->rta_gw == NULL)
		return -EINVAL;

	if (rtm->rtm_scope == RT_SCOPE_NOWHERE)
		rtm->rtm_scope = RT_SCOPE_LINK;

	if (r->rt_flags&(RTF_MTU|RTF_WINDOW|RTF_IRTT)) {
		struct rtattr *rec;
		struct rtattr *mx = kmalloc(RTA_LENGTH(3*RTA_LENGTH(4)), GFP_KERNEL);
		if (mx == NULL)
			return -ENOMEM;
		rta->rta_mx = mx;
		mx->rta_type = RTA_METRICS;
		mx->rta_len  = RTA_LENGTH(0);
		if (r->rt_flags&RTF_MTU) {
			rec = (void*)((char*)mx + RTA_ALIGN(mx->rta_len));
			rec->rta_type = RTAX_ADVMSS;
			rec->rta_len = RTA_LENGTH(4);
			mx->rta_len += RTA_LENGTH(4);
			*(u32*)RTA_DATA(rec) = r->rt_mtu - 40;
		}
		if (r->rt_flags&RTF_WINDOW) {
			rec = (void*)((char*)mx + RTA_ALIGN(mx->rta_len));
			rec->rta_type = RTAX_WINDOW;
			rec->rta_len = RTA_LENGTH(4);
			mx->rta_len += RTA_LENGTH(4);
			*(u32*)RTA_DATA(rec) = r->rt_window;
		}
		if (r->rt_flags&RTF_IRTT) {
			rec = (void*)((char*)mx + RTA_ALIGN(mx->rta_len));
			rec->rta_type = RTAX_RTT;
			rec->rta_len = RTA_LENGTH(4);
			mx->rta_len += RTA_LENGTH(4);
			*(u32*)RTA_DATA(rec) = r->rt_irtt<<3;
		}
	}
	return 0;
}

#endif

/*
   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(u32 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(dev) == NULL)
				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