Currently inet_addr_type and inet_dev_addr_type expect local addresses
to be in the local table. With the VRF device local routes for devices
associated with a VRF will be in the table associated with the VRF.
Provide an alternate inet_addr lookup to use a specific table rather
than defaulting to the local table.
inet_addr_type_dev_table keeps the same semantics as inet_addr_type but
if the passed in device is enslaved to a VRF then the table for that VRF
is used for the lookup.
Signed-off-by: David Ahern <d...@cumulusnetworks.com>
---
include/net/route.h | 3 +++
net/ipv4/af_inet.c | 13 ++++++++++++-
net/ipv4/arp.c | 15 +++++++++------
net/ipv4/fib_frontend.c | 28 +++++++++++++++++++++++++---
net/ipv4/fib_semantics.c | 6 ++++--
net/ipv4/icmp.c | 5 +++--
6 files changed, 56 insertions(+), 14 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index 6ba681f0b98d..6dda2c1bf8c6 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -192,6 +192,9 @@ unsigned int inet_addr_type(struct net *net, __be32 addr);
unsigned int inet_addr_type_table(struct net *net, __be32 addr, int tb_id);
unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev,
__be32 addr);
+unsigned int inet_addr_type_dev_table(struct net *net,
+ const struct net_device *dev,
+ __be32 addr);
void ip_rt_multicast_event(struct in_device *);
int ip_rt_ioctl(struct net *, unsigned int cmd, void __user *arg);
void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index cc4e498a0ccf..96fba4f63454 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -119,6 +119,7 @@
#ifdef CONFIG_IP_MROUTE
#include <linux/mroute.h>
#endif
+#include <net/vrf.h>
/* The inetsw table contains everything that inet_create needs to
@@ -427,6 +428,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr,
int addr_len)
struct net *net = sock_net(sk);
unsigned short snum;
int chk_addr_ret;
+ int tb_id = 0;
int err;
/* If the socket has its own bind function then use it. (RAW) */
@@ -448,7 +450,16 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr,
int addr_len)
goto out;
}
- chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr);
+ if (sk->sk_bound_dev_if) {
+ struct net_device *dev;
+
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
+ if (dev)
+ tb_id = vrf_dev_table_rcu(dev);
+ rcu_read_unlock();
+ }
+ chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id);
/* Not specified by any standard per-se, however it breaks too
* many applications when removed. It is unfortunate since
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 34a308573f4b..30409b75e925 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -233,7 +233,7 @@ static int arp_constructor(struct neighbour *neigh)
return -EINVAL;
}
- neigh->type = inet_addr_type(dev_net(dev), addr);
+ neigh->type = inet_addr_type_dev_table(dev_net(dev), dev, addr);
parms = in_dev->arp_parms;
__neigh_parms_put(neigh->parms);
@@ -343,7 +343,7 @@ static void arp_solicit(struct neighbour *neigh, struct
sk_buff *skb)
switch (IN_DEV_ARP_ANNOUNCE(in_dev)) {
default:
case 0: /* By default announce any local IP */
- if (skb && inet_addr_type(dev_net(dev),
+ if (skb && inet_addr_type_dev_table(dev_net(dev), dev,
ip_hdr(skb)->saddr) == RTN_LOCAL)
saddr = ip_hdr(skb)->saddr;
break;
@@ -351,7 +351,8 @@ static void arp_solicit(struct neighbour *neigh, struct
sk_buff *skb)
if (!skb)
break;
saddr = ip_hdr(skb)->saddr;
- if (inet_addr_type(dev_net(dev), saddr) == RTN_LOCAL) {
+ if (inet_addr_type_dev_table(dev_net(dev), dev,
+ saddr) == RTN_LOCAL) {
/* saddr should be known to target */
if (inet_addr_onlink(in_dev, target, saddr))
break;
@@ -751,7 +752,7 @@ static int arp_process(struct sock *sk, struct sk_buff *skb)
/* Special case: IPv4 duplicate address detection packet (RFC2131) */
if (sip == 0) {
if (arp->ar_op == htons(ARPOP_REQUEST) &&
- inet_addr_type(net, tip) == RTN_LOCAL &&
+ inet_addr_type_dev_table(net, dev, tip) == RTN_LOCAL &&
!arp_ignore(in_dev, sip, tip))
arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha,
dev->dev_addr, sha);
@@ -811,16 +812,18 @@ static int arp_process(struct sock *sk, struct sk_buff
*skb)
n = __neigh_lookup(&arp_tbl, &sip, dev, 0);
if (IN_DEV_ARP_ACCEPT(in_dev)) {
+ unsigned int addr_type = inet_addr_type_dev_table(net, dev,
sip);
+
/* Unsolicited ARP is not accepted by default.
It is possible, that this option should be enabled for some
devices (strip is candidate)
*/
is_garp = arp->ar_op == htons(ARPOP_REQUEST) && tip == sip &&
- inet_addr_type(net, sip) == RTN_UNICAST;
+ addr_type == RTN_UNICAST;
if (!n &&
((arp->ar_op == htons(ARPOP_REPLY) &&
- inet_addr_type(net, sip) == RTN_UNICAST) || is_garp))
+ addr_type == RTN_UNICAST) || is_garp))
n = __neigh_lookup(&arp_tbl, &sip, dev, 1);
}
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index b11321a8e58d..d84ae0e30369 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -226,6 +226,9 @@ static inline unsigned int __inet_dev_addr_type(struct net
*net,
rcu_read_lock();
+ if (!tb_id)
+ tb_id = RT_TABLE_LOCAL;
+
table = fib_get_table(net, tb_id);
if (table) {
ret = RTN_UNICAST;
@@ -260,6 +263,19 @@ unsigned int inet_dev_addr_type(struct net *net, const
struct net_device *dev,
}
EXPORT_SYMBOL(inet_dev_addr_type);
+/* inet_addr_type with dev == NULL but using the table from a dev
+ * if one is associated
+ */
+unsigned int inet_addr_type_dev_table(struct net *net,
+ const struct net_device *dev,
+ __be32 addr)
+{
+ int rt_table = vrf_dev_table(dev) ? : RT_TABLE_LOCAL;
+
+ return __inet_dev_addr_type(net, NULL, addr, rt_table);
+}
+EXPORT_SYMBOL(inet_addr_type_dev_table);
+
__be32 fib_compute_spec_dst(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
@@ -510,9 +526,12 @@ static int rtentry_to_fib_config(struct net *net, int cmd,
struct rtentry *rt,
addr = sk_extract_addr(&rt->rt_gateway);
if (rt->rt_gateway.sa_family == AF_INET && addr) {
+ unsigned int addr_type;
+
cfg->fc_gw = addr;
+ addr_type = inet_addr_type_table(net, cfg->fc_table, addr);
if (rt->rt_flags & RTF_GATEWAY &&
- inet_addr_type(net, addr) == RTN_UNICAST)
+ addr_type == RTN_UNICAST)
cfg->fc_scope = RT_SCOPE_UNIVERSE;
}
@@ -984,11 +1003,14 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct
in_ifaddr *iprim)
fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim);
}
if (!(ok & LOCAL_OK)) {
+ unsigned int addr_type;
+
fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim);
/* Check, that this local address finally disappeared. */
- if (gone &&
- inet_addr_type(dev_net(dev), ifa->ifa_local) != RTN_LOCAL) {
+ addr_type = inet_addr_type_dev_table(dev_net(dev), dev,
+ ifa->ifa_local);
+ if (gone && addr_type != RTN_LOCAL) {
/* And the last, but not the least thing.
* We must flush stray FIB entries.
*
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 558e196bae0f..410ddb67221e 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -670,16 +670,18 @@ static int fib_check_nh(struct fib_config *cfg, struct
fib_info *fi,
struct fib_result res;
if (nh->nh_flags & RTNH_F_ONLINK) {
+ unsigned int addr_type;
if (cfg->fc_scope >= RT_SCOPE_LINK)
return -EINVAL;
- if (inet_addr_type(net, nh->nh_gw) != RTN_UNICAST)
- return -EINVAL;
dev = __dev_get_by_index(net, nh->nh_oif);
if (!dev)
return -ENODEV;
if (!(dev->flags & IFF_UP))
return -ENETDOWN;
+ addr_type = inet_addr_type_dev_table(net, dev,
nh->nh_gw);
+ if (addr_type != RTN_UNICAST)
+ return -EINVAL;
if (!netif_carrier_ok(dev))
nh->nh_flags |= RTNH_F_LINKDOWN;
nh->nh_dev = dev;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 1164fc4ce3bc..c6f1ce149ffb 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -484,7 +484,8 @@ static struct rtable *icmp_route_lookup(struct net *net,
if (err)
goto relookup_failed;
- if (inet_addr_type(net, fl4_dec.saddr) == RTN_LOCAL) {
+ if (inet_addr_type_dev_table(net, skb_in->dev,
+ fl4_dec.saddr) == RTN_LOCAL) {
rt2 = __ip_route_output_key(net, &fl4_dec);
if (IS_ERR(rt2))
err = PTR_ERR(rt2);
@@ -833,7 +834,7 @@ static bool icmp_unreach(struct sk_buff *skb)
*/
if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses &&
- inet_addr_type(net, iph->daddr) == RTN_BROADCAST) {
+ inet_addr_type_dev_table(net, skb->dev, iph->daddr) ==
RTN_BROADCAST) {
net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code
%u error to a broadcast: %pI4 on %s\n",
&ip_hdr(skb)->saddr,
icmph->type, icmph->code,
--
2.3.2 (Apple Git-55)
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
