Re: [PATCH 1/1] ipv6: RTA_PREFSRC support for ipv6 route source addressselection

From: Stephen Clark
Date: Thu Apr 14 2011 - 10:01:32 EST

On 04/14/2011 03:10 AM, Daniel Walter wrote:
[ipv6] Add support for RTA_PREFSRC

This patch allows a user to select the preferred source address
for a specific IPv6-Route. It can be set via a netlink message
setting RTA_PREFSRC to a valid IPv6 address which must be
up on the device the route will be bound to.


Signed-off-by: Daniel Walter<dwalter@xxxxxxxxxxxxx>
---
Repost patch, after fixing some warnings pointed out on netdev@
applies clean against current linux-2.6 HEAD

include/net/ip6_fib.h | 2 +
include/net/ip6_route.h | 7 ++++
net/ipv6/addrconf.c | 2 +
net/ipv6/ip6_output.c | 8 ++--
net/ipv6/route.c | 72 +++++++++++++++++++++++++++++++++++++++++++++--
5 files changed, 84 insertions(+), 7 deletions(-)

---
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index bc3cde0..98348d5 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -42,6 +42,7 @@ struct fib6_config {

struct in6_addr fc_dst;
struct in6_addr fc_src;
+ struct in6_addr fc_prefsrc;
struct in6_addr fc_gateway;

unsigned long fc_expires;
@@ -107,6 +108,7 @@ struct rt6_info {
struct rt6key rt6i_dst ____cacheline_aligned_in_smp;
u32 rt6i_flags;
struct rt6key rt6i_src;
+ struct rt6key rt6i_prefsrc;
u32 rt6i_metric;
u32 rt6i_peer_genid;

diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index c850e5f..86b1cb4 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -84,6 +84,12 @@ extern int ip6_route_add(struct fib6_config *cfg);
extern int ip6_ins_rt(struct rt6_info *);
extern int ip6_del_rt(struct rt6_info *);

+extern int ip6_route_get_saddr(struct net *net,
+ struct rt6_info *rt,
+ struct in6_addr *daddr,
+ unsigned int prefs,
+ struct in6_addr *saddr);
+
extern struct rt6_info *rt6_lookup(struct net *net,
const struct in6_addr *daddr,
const struct in6_addr *saddr,
@@ -141,6 +147,7 @@ struct rt6_rtnl_dump_arg {
extern int rt6_dump_route(struct rt6_info *rt, void *p_arg);
extern void rt6_ifdown(struct net *net, struct net_device *dev);
extern void rt6_mtu_change(struct net_device *dev, unsigned mtu);
+extern void rt6_remove_prefsrc(struct inet6_ifaddr *ifp);


/*
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 1493534..129d7e1 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -825,6 +825,8 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
dst_release(&rt->dst);
}

+ /* clean up prefsrc entries */
+ rt6_remove_prefsrc(ifp);
out:
in6_ifa_put(ifp);
}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 46cf7be..1f4c096 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -930,10 +930,10 @@ static int ip6_dst_lookup_tail(struct sock *sk,
goto out_err_release;

if (ipv6_addr_any(&fl6->saddr)) {
- err = ipv6_dev_get_saddr(net, ip6_dst_idev(*dst)->dev,
- &fl6->daddr,
- sk ? inet6_sk(sk)->srcprefs : 0,
- &fl6->saddr);
+ struct rt6_info *rt = (struct rt6_info *) *dst;
+ err = ip6_route_get_saddr(net, rt,&fl6->daddr,
+ sk ? inet6_sk(sk)->srcprefs : 0,
+ &fl6->saddr);
if (err)
goto out_err_release;
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 843406f..af26cc10 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1325,6 +1325,16 @@ int ip6_route_add(struct fib6_config *cfg)
if (dev == NULL)
goto out;

+ if (!ipv6_addr_any(&cfg->fc_prefsrc)) {
+ if (!ipv6_chk_addr(net,&cfg->fc_prefsrc, dev, 0)) {
+ err = -EINVAL;
+ goto out;
+ }
+ ipv6_addr_copy(&rt->rt6i_prefsrc.addr,&cfg->fc_prefsrc);
+ rt->rt6i_prefsrc.plen = 128;
+ } else
+ rt->rt6i_prefsrc.plen = 0;
+
if (cfg->fc_flags& (RTF_GATEWAY | RTF_NONEXTHOP)) {
rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl,&rt->rt6i_gateway, dev);
if (IS_ERR(rt->rt6i_nexthop)) {
@@ -2037,6 +2047,55 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
return rt;
}

+int ip6_route_get_saddr(struct net *net,
+ struct rt6_info *rt,
+ struct in6_addr *daddr,
+ unsigned int prefs,
+ struct in6_addr *saddr)
+{
+ struct inet6_dev *idev = ip6_dst_idev((struct dst_entry*)rt);
+ int err = 0;
+ if (rt->rt6i_prefsrc.plen)
+ ipv6_addr_copy(saddr,&rt->rt6i_prefsrc.addr);
+ else
+ err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
+ daddr, prefs, saddr);
+ return err;
+}
+
+/* remove deleted ip from prefsrc entries */
+struct arg_dev_net_ip {
+ struct net_device *dev;
+ struct net *net;
+ struct in6_addr *addr;
+};
+
+static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg)
+{
+ struct net_device *dev = ((struct arg_dev_net_ip *)arg)->dev;
+ struct net *net = ((struct arg_dev_net_ip *)arg)->net;
+ struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
+
+ if (((void *)rt->rt6i_dev == dev || dev == NULL)&&
+ rt != net->ipv6.ip6_null_entry&&
+ ipv6_addr_equal(addr,&rt->rt6i_prefsrc.addr)) {
+ /* remove prefsrc entry */
+ rt->rt6i_prefsrc.plen = 0;
+ }
+ return 0;
+}
+
+void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
+{
+ struct net *net = dev_net(ifp->idev->dev);
+ struct arg_dev_net_ip adni = {
+ .dev = ifp->idev->dev,
+ .net = net,
+ .addr =&ifp->addr,
+ };
+ fib6_clean_all(net, fib6_remove_prefsrc, 0,&adni);
+}
+
struct arg_dev_net {
struct net_device *dev;
struct net *net;
@@ -2183,6 +2242,9 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen);
}

+ if (tb[RTA_PREFSRC])
+ nla_memcpy(&cfg->fc_prefsrc, tb[RTA_PREFSRC], 16);
+
if (tb[RTA_OIF])
cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]);

@@ -2325,13 +2387,17 @@ static int rt6_fill_node(struct net *net,
#endif
NLA_PUT_U32(skb, RTA_IIF, iif);
} else if (dst) {
- struct inet6_dev *idev = ip6_dst_idev(&rt->dst);
struct in6_addr saddr_buf;
- if (ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
- dst, 0,&saddr_buf) == 0)
+ if (ip6_route_get_saddr(net, rt, dst, 0,&saddr_buf) == 0)
NLA_PUT(skb, RTA_PREFSRC, 16,&saddr_buf);
}

+ if (rt->rt6i_prefsrc.plen) {
+ struct in6_addr saddr_buf;
+ ipv6_addr_copy(&saddr_buf,&rt->rt6i_prefsrc.addr);
+ NLA_PUT(skb, RTA_PREFSRC, 16,&saddr_buf);
+ }
+
if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst))< 0)
goto nla_put_failure;

What userspace application will be used to set this?
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/