ANDROID: net: ipv6: autoconf routes into per-device tables

Currently, IPv6 router discovery always puts routes into
RT6_TABLE_MAIN. This causes problems for connection managers
that want to support multiple simultaneous network connections
and want control over which one is used by default (e.g., wifi
and wired).

To work around this connection managers typically take the routes
they prefer and copy them to static routes with low metrics in
the main table. This puts the burden on the connection manager
to watch netlink to see if the routes have changed, delete the
routes when their lifetime expires, etc.

Instead, this patch adds a per-interface sysctl to have the
kernel put autoconf routes into different tables. This allows
each interface to have its own autoconf table, and choosing the
default interface (or using different interfaces at the same
time for different types of traffic) can be done using
appropriate ip rules.

The sysctl behaves as follows:

- = 0: default. Put routes into RT6_TABLE_MAIN as before.
- > 0: manual. Put routes into the specified table.
- < 0: automatic. Add the absolute value of the sysctl to the
       device's ifindex, and use that table.

The automatic mode is most useful in conjunction with
net.ipv6.conf.default.accept_ra_rt_table. A connection manager
or distribution could set it to, say, -100 on boot, and
thereafter just use IP rules.

Change-Id: I82d16e3737d9cdfa6489e649e247894d0d60cbb1
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
[AmitP: Refactored original changes to align with
        the changes introduced by upstream commit
        830218c1add1 ("net: ipv6: Fix processing of RAs in presence of VRF")

        Also folded following android-4.9 commit changes into this patch
        be65fb01da4d ("ANDROID: net: ipv6: remove unused variable ifindex in")]
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index ea04ca024f0d2ad21fa3840b4baf4a397517b421..cfd0cc15832619a746d15d9624fb9422a4307947 100644 (file)
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -42,6 +42,7 @@ struct ipv6_devconf {
        __s32           accept_ra_rt_info_max_plen;
 #endif
 #endif
+       __s32           accept_ra_rt_table;
        __s32           proxy_ndp;
        __s32           accept_source_route;
        __s32           accept_ra_from_local;

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 35f5aabd432ff8212b99094e13bb65b64830782f..bcd9b88bc4e8c58c4f48e3acfa6a410ca34c5716 100644 (file)
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -261,6 +261,8 @@ static inline bool ipv6_is_mld(struct sk_buff *skb, int nexthdr, int offset)
 void addrconf_prefix_rcv(struct net_device *dev,
                         u8 *opt, int len, bool sllao);
 
+u32 addrconf_rt_table(const struct net_device *dev, u32 default_table);
+
 /*
  *     anycast prototypes (anycast.c)
  */

diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index b22a9c4e1b1248d73938fb271e83b516292130a1..8c3ea81d5bd77939a3f8f6a68db9c2529aa8ec7c 100644 (file)
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -166,6 +166,7 @@ enum {
        DEVCONF_ACCEPT_DAD,
        DEVCONF_FORCE_TLLAO,
        DEVCONF_NDISC_NOTIFY,
+       DEVCONF_ACCEPT_RA_RT_TABLE,
        DEVCONF_MLDV1_UNSOLICITED_REPORT_INTERVAL,
        DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL,
        DEVCONF_SUPPRESS_FRAG_NDISC,

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 8a1c846d3df949a4638589f187120db22a3525ba..135c8703047ced9518390c0e692b324f8be83a1e 100644 (file)
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -228,6 +228,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
        .accept_ra_rt_info_max_plen = 0,
 #endif
 #endif
+       .accept_ra_rt_table     = 0,
        .proxy_ndp              = 0,
        .accept_source_route    = 0,    /* we do not accept RH0 by default. */
        .disable_ipv6           = 0,
@@ -282,6 +283,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
        .accept_ra_rt_info_max_plen = 0,
 #endif
 #endif
+       .accept_ra_rt_table     = 0,
        .proxy_ndp              = 0,
        .accept_source_route    = 0,    /* we do not accept RH0 by default. */
        .disable_ipv6           = 0,
@@ -2273,6 +2275,31 @@ static void  ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpad
                ipv6_regen_rndid(idev);
 }
 
+u32 addrconf_rt_table(const struct net_device *dev, u32 default_table) {
+       /* Determines into what table to put autoconf PIO/RIO/default routes
+        * learned on this device.
+        *
+        * - If 0, use the same table for every device. This puts routes into
+        *   one of RT_TABLE_{PREFIX,INFO,DFLT} depending on the type of route
+        *   (but note that these three are currently all equal to
+        *   RT6_TABLE_MAIN).
+        * - If > 0, use the specified table.
+        * - If < 0, put routes into table dev->ifindex + (-rt_table).
+        */
+       struct inet6_dev *idev = in6_dev_get(dev);
+       u32 table;
+       int sysctl = idev->cnf.accept_ra_rt_table;
+       if (sysctl == 0) {
+               table = default_table;
+       } else if (sysctl > 0) {
+               table = (u32) sysctl;
+       } else {
+               table = (unsigned) dev->ifindex + (-sysctl);
+       }
+       in6_dev_put(idev);
+       return table;
+}
+
 /*
  *     Add prefix route.
  */
@@ -2282,7 +2309,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
                      unsigned long expires, u32 flags)
 {
        struct fib6_config cfg = {
-               .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX,
+               .fc_table = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_PREFIX),
                .fc_metric = IP6_RT_PRIO_ADDRCONF,
                .fc_ifindex = dev->ifindex,
                .fc_expires = expires,
@@ -2315,7 +2342,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
        struct fib6_node *fn;
        struct rt6_info *rt = NULL;
        struct fib6_table *table;
-       u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX;
+       u32 tb_id = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_PREFIX);
 
        table = fib6_get_table(dev_net(dev), tb_id);
        if (!table)
@@ -5021,6 +5048,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
        array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen;
 #endif
 #endif
+       array[DEVCONF_ACCEPT_RA_RT_TABLE] = cnf->accept_ra_rt_table;
        array[DEVCONF_PROXY_NDP] = cnf->proxy_ndp;
        array[DEVCONF_ACCEPT_SOURCE_ROUTE] = cnf->accept_source_route;
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
@@ -6180,6 +6208,13 @@ static const struct ctl_table addrconf_sysctl[] = {
        },
 #endif
 #endif
+       {
+               .procname       = "accept_ra_rt_table",
+               .data           = &ipv6_devconf.accept_ra_rt_table,
+               .maxlen         = sizeof(int),
+               .mode           = 0644,
+               .proc_handler   = proc_dointvec,
+       },
        {
                .procname       = "proxy_ndp",
                .data           = &ipv6_devconf.proxy_ndp,

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a96d5b385d8fa25bab416d3f6bc836e743b3ca99..278271d6bd47d7329519b0aa3b20bf042bb767b1 100644 (file)
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2501,8 +2501,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
                                           const struct in6_addr *gwaddr,
                                           struct net_device *dev)
 {
-       u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO;
-       int ifindex = dev->ifindex;
+       u32 tb_id = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_INFO);
        struct fib6_node *fn;
        struct rt6_info *rt = NULL;
        struct fib6_table *table;
@@ -2517,7 +2516,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
                goto out;
 
        for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
-               if (rt->dst.dev->ifindex != ifindex)
+               if (rt->dst.dev->ifindex != dev->ifindex)
                        continue;
                if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
                        continue;
@@ -2549,7 +2548,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
                .fc_nlinfo.nl_net = net,
        };
 
-       cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO,
+       cfg.fc_table = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_INFO),
        cfg.fc_dst = *prefix;
        cfg.fc_gateway = *gwaddr;
 
@@ -2565,7 +2564,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
 
 struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_device *dev)
 {
-       u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT;
+       u32 tb_id = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_MAIN);
        struct rt6_info *rt;
        struct fib6_table *table;
 
@@ -2591,7 +2590,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
                                     unsigned int pref)
 {
        struct fib6_config cfg = {
-               .fc_table       = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT,
+               .fc_table       = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_DFLT),
                .fc_metric      = IP6_RT_PRIO_USER,
                .fc_ifindex     = dev->ifindex,
                .fc_flags       = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
@@ -2615,43 +2614,16 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
        return rt6_get_dflt_router(gwaddr, dev);
 }
 
-static void __rt6_purge_dflt_routers(struct fib6_table *table)
-{
-       struct rt6_info *rt;
-
-restart:
-       read_lock_bh(&table->tb6_lock);
-       for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
-               if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
-                   (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) {
-                       dst_hold(&rt->dst);
-                       read_unlock_bh(&table->tb6_lock);
-                       ip6_del_rt(rt);
-                       goto restart;
-               }
-       }
-       read_unlock_bh(&table->tb6_lock);
-
-       table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER;
+int rt6_addrconf_purge(struct rt6_info *rt, void *arg) {
+       if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
+           (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2))
+               return -1;
+       return 0;
 }
 
 void rt6_purge_dflt_routers(struct net *net)
 {
-       struct fib6_table *table;
-       struct hlist_head *head;
-       unsigned int h;
-
-       rcu_read_lock();
-
-       for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
-               head = &net->ipv6.fib_table_hash[h];
-               hlist_for_each_entry_rcu(table, head, tb6_hlist) {
-                       if (table->flags & RT6_TABLE_HAS_DFLT_ROUTER)
-                               __rt6_purge_dflt_routers(table);
-               }
-       }
-
-       rcu_read_unlock();
+       fib6_clean_all(net, rt6_addrconf_purge, NULL);
 }
 
 static void rtmsg_to_fib6_config(struct net *net,