Merge branch 'cached-route-listings'

Stefano Brivio says:

====================
Fix listing (IPv4, IPv6) and flushing (IPv6) of cached route exceptions

For IPv6 cached routes, the commands 'ip -6 route list cache' and
'ip -6 route flush cache' don't work at all after route exceptions have
been moved to a separate hash table in commit 2b760fcf5cfb ("ipv6: hook
up exception table to store dst cache").

For IPv4 cached routes, the command 'ip route list cache' has also
stopped working in kernel 3.5 after commit 4895c771c7f0 ("ipv4: Add FIB
nexthop exceptions.") introduced storage for route exceptions as a
separate entity.

Fix this by allowing userspace to clearly request cached routes with
the RTM_F_CLONED flag used as a filter (in conjuction with strict
checking) and by retrieving and dumping cached routes if requested.

If strict checking is not requested (iproute2 < 5.0.0), we don't have a
way to consistently filter results on other selectors (e.g. on tables),
so skip filtering entirely and dump both regular routes and exceptions.

For IPv4, cache flushing uses a completely different mechanism, so it
wasn't affected. Listing of exception routes (modified routes pre-3.5) was
tested against these versions of kernel and iproute2:

                    iproute2
kernel         4.14.0   4.15.0   4.19.0   5.0.0   5.1.0
 3.5-rc4         +        +        +        +       +
 4.4
 4.9
 4.14
 4.15
 4.19
 5.0
 5.1
 fixed           +        +        +        +       +

For IPv6, a separate iproute2 patch is required. Versions of iproute2
and kernel tested:

                    iproute2
kernel             4.14.0   4.15.0   4.19.0   5.0.0   5.1.0    5.1.0, patched
 3.18    list        +        +        +        +       +            +
         flush       +        +        +        +       +            +
 4.4     list        +        +        +        +       +            +
         flush       +        +        +        +       +            +
 4.9     list        +        +        +        +       +            +
         flush       +        +        +        +       +            +
 4.14    list        +        +        +        +       +            +
         flush       +        +        +        +       +            +
 4.15    list
         flush
 4.19    list
         flush
 5.0     list
         flush
 5.1     list
         flush
 with    list        +        +        +        +       +            +
 fix     flush       +        +        +                             +

v7: Make sure r->rtm_tos is initialised in 3/11, move loop over nexthop
    objects in 4/11, add comments about usage of "skip" counters in commit
    messages of 4/11 and 8/11

v6: Target for net-next, rebase and adapt to nexthop objects for IPv6 paths.
    Merge selftests into this series (as they were addressed for net-next).
    A number of minor changes detailed in logs of single patches.

v5: Skip filtering altogether if no strict checking is requested: selecting
    routes or exceptions only would be inconsistent with the fact we can't
    filter on tables. Drop 1/8 (non-strict dump filter function no longer
    needed), replace 2/8 (don't use NLM_F_MATCH, decide to skip routes or
    exceptions in filter function), drop 6/8 (2/8 is enough for IPv6 too).
    Introduce dump_routes and dump_exceptions flags in filter, adapt other
    patches to that.

v4: Fix the listing issue also for IPv4, making the behaviour consistent
    with IPv6. Honour NLM_F_MATCH as per RFC 3549 and allow usage of
    RTM_F_CLONED filter. Split patches into smaller logical changes.

v3: Drop check on RTM_F_CLONED and rework logic of return values of
    rt6_dump_route()

v2: Add count of routes handled in partial dumps, and skip them, in patch 1/2.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 8 insertions, 1 deletions

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 87331f2c4af0..4b5656c71abc 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -316,6 +316,7 @@ struct fib6_walker {
 	enum fib6_walk_state state;
 	unsigned int skip;
 	unsigned int count;
+	unsigned int skip_in_node;
 	int (*func)(struct fib6_walker *);
 	void *args;
 };
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 89ad7917b98d..c8bba0c28286 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -197,7 +197,7 @@ struct rt6_rtnl_dump_arg {
 	struct fib_dump_filter filter;
 };
 
-int rt6_dump_route(struct fib6_info *f6i, void *p_arg);
+int rt6_dump_route(struct fib6_info *f6i, void *p_arg, unsigned int skip);
 void rt6_mtu_change(struct net_device *dev, unsigned int mtu);
 void rt6_remove_prefsrc(struct inet6_ifaddr *ifp);
 void rt6_clean_tohost(struct net *net, struct in6_addr *gateway);
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 7e1e621a56df..4c81846ccce8 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -245,6 +245,8 @@ struct fib_dump_filter {
 	/* filter_set is an optimization that an entry is set */
 	bool			filter_set;
 	bool			dump_all_families;
+	bool			dump_routes;
+	bool			dump_exceptions;
 	unsigned char		protocol;
 	unsigned char		rt_type;
 	unsigned int		flags;
diff --git a/include/net/route.h b/include/net/route.h
index 065b47754f05..cfcd0f5980f9 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -230,6 +230,10 @@ void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric);
 void rt_add_uncached_list(struct rtable *rt);
 void rt_del_uncached_list(struct rtable *rt);
 
+int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb,
+		       u32 table_id, struct fib_info *fi,
+		       int *fa_index, int fa_start);
+
 static inline void ip_rt_put(struct rtable *rt)
 {
 	/* dst_release() accepts a NULL parameter.