[PATCH v2 net] ipv6: fix src addr routing with the exception table

[PATCH v2 net] ipv6: fix src addr routing with the exception table

[Wei Wang]

From: Wei Wang <weiwan@google.com>

When inserting route cache into the exception table, the key is
generated with both src_addr and dest_addr with src addr routing.
However, current logic always assumes the src_addr used to generate the
key is a /128 host address. This is not true in the following scenarios:
1. When the route is a gateway route or does not have next hop.
   (rt6_is_gw_or_nonexthop() == false)
2. When calling ip6_rt_cache_alloc(), saddr is passed in as NULL.
This means, when looking for a route cache in the exception table, we
have to do the lookup twice: first time with the passed in /128 host
address, second time with the src_addr stored in fib6_info.

This solves the pmtu discovery issue reported by Mikael Magnusson where
a route cache with a lower mtu info is created for a gateway route with
src addr. However, the lookup code is not able to find this route cache.

Fixes: 2b760fcf5cfb ("ipv6: hook up exception table to store dst cache")
Reported-by: Mikael Magnusson <mikael.kernel@lists.m7n.se>
Bisected-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Wei Wang <weiwan@google.com>
Cc: Martin Lau <kafai@fb.com>
Cc: Eric Dumazet <edumazet@google.com>
---
Changes from v1:
- restructure the code to only include the new logic in
  rt6_find_cached_rt()
---
 net/ipv6/route.c | 49 +++++++++++++++++++++++++-----------------------
 1 file changed, 26 insertions(+), 23 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 23a20d62daac..35873b57c7f1 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -111,8 +111,8 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 			 int iif, int type, u32 portid, u32 seq,
 			 unsigned int flags);
 static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
-					   struct in6_addr *daddr,
-					   struct in6_addr *saddr);
+					   const struct in6_addr *daddr,
+					   const struct in6_addr *saddr);
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
 static struct fib6_info *rt6_add_route_info(struct net *net,
@@ -1566,31 +1566,44 @@ void rt6_flush_exceptions(struct fib6_info *rt)
  * Caller has to hold rcu_read_lock()
  */
 static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
-					   struct in6_addr *daddr,
-					   struct in6_addr *saddr)
+					   const struct in6_addr *daddr,
+					   const struct in6_addr *saddr)
 {
 	struct rt6_exception_bucket *bucket;
 	struct in6_addr *src_key = NULL;
 	struct rt6_exception *rt6_ex;
 	struct rt6_info *ret = NULL;
 
-	bucket = rcu_dereference(res->f6i->rt6i_exception_bucket);
-
 #ifdef CONFIG_IPV6_SUBTREES
 	/* fib6i_src.plen != 0 indicates f6i is in subtree
 	 * and exception table is indexed by a hash of
 	 * both fib6_dst and fib6_src.
-	 * Otherwise, the exception table is indexed by
-	 * a hash of only fib6_dst.
+	 * However, the src addr used to create the hash
+	 * might not be exactly the passed in saddr which
+	 * is a /128 addr from the flow.
+	 * So we need to use f6i->fib6_src to redo lookup
+	 * if the passed in saddr does not find anything.
+	 * (See the logic in ip6_rt_cache_alloc() on how
+	 * rt->rt6i_src is updated.)
 	 */
 	if (res->f6i->fib6_src.plen)
 		src_key = saddr;
+find_ex:
 #endif
+	bucket = rcu_dereference(res->f6i->rt6i_exception_bucket);
 	rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
 
 	if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
 		ret = rt6_ex->rt6i;
 
+#ifdef CONFIG_IPV6_SUBTREES
+	/* Use fib6_src as src_key and redo lookup */
+	if (!ret && src_key == saddr) {
+		src_key = &res->f6i->fib6_src.addr;
+		goto find_ex;
+	}
+#endif
+
 	return ret;
 }
 
@@ -2665,12 +2678,10 @@ u32 ip6_mtu_from_fib6(const struct fib6_result *res,
 		      const struct in6_addr *daddr,
 		      const struct in6_addr *saddr)
 {
-	struct rt6_exception_bucket *bucket;
 	const struct fib6_nh *nh = res->nh;
 	struct fib6_info *f6i = res->f6i;
-	const struct in6_addr *src_key;
-	struct rt6_exception *rt6_ex;
 	struct inet6_dev *idev;
+	struct rt6_info *rt;
 	u32 mtu = 0;
 
 	if (unlikely(fib6_metric_locked(f6i, RTAX_MTU))) {
@@ -2679,18 +2690,10 @@ u32 ip6_mtu_from_fib6(const struct fib6_result *res,
 			goto out;
 	}
 
-	src_key = NULL;
-#ifdef CONFIG_IPV6_SUBTREES
-	if (f6i->fib6_src.plen)
-		src_key = saddr;
-#endif
-
-	bucket = rcu_dereference(f6i->rt6i_exception_bucket);
-	rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
-	if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
-		mtu = dst_metric_raw(&rt6_ex->rt6i->dst, RTAX_MTU);
-
-	if (likely(!mtu)) {
+	rt = rt6_find_cached_rt(res, daddr, saddr);
+	if (unlikely(rt)) {
+		mtu = dst_metric_raw(&rt->dst, RTAX_MTU);
+	} else {
 		struct net_device *dev = nh->fib_nh_dev;
 
 		mtu = IPV6_MIN_MTU;
-- 
2.21.0.1020.gf2820cf01a-goog

Re: [PATCH v2 net] ipv6: fix src addr routing with the exception table

[Martin Lau]

On Thu, May 16, 2019 at 11:16:20AM -0700, Wei Wang wrote:
> From: Wei Wang <weiwan@google.com>
> 
> When inserting route cache into the exception table, the key is
> generated with both src_addr and dest_addr with src addr routing.
> However, current logic always assumes the src_addr used to generate the
> key is a /128 host address. This is not true in the following scenarios:
> 1. When the route is a gateway route or does not have next hop.
>    (rt6_is_gw_or_nonexthop() == false)
> 2. When calling ip6_rt_cache_alloc(), saddr is passed in as NULL.
> This means, when looking for a route cache in the exception table, we
> have to do the lookup twice: first time with the passed in /128 host
> address, second time with the src_addr stored in fib6_info.
> 
> This solves the pmtu discovery issue reported by Mikael Magnusson where
> a route cache with a lower mtu info is created for a gateway route with
> src addr. However, the lookup code is not able to find this route cache.
> 
> Fixes: 2b760fcf5cfb ("ipv6: hook up exception table to store dst cache")
> Reported-by: Mikael Magnusson <mikael.kernel@lists.m7n.se>
> Bisected-by: David Ahern <dsahern@gmail.com>
> Signed-off-by: Wei Wang <weiwan@google.com>
> Cc: Martin Lau <kafai@fb.com>
> Cc: Eric Dumazet <edumazet@google.com>
> ---
> Changes from v1:
> - restructure the code to only include the new logic in
>   rt6_find_cached_rt()
> ---
>  net/ipv6/route.c | 49 +++++++++++++++++++++++++-----------------------
>  1 file changed, 26 insertions(+), 23 deletions(-)
> 
> diff --git a/net/ipv6/route.c b/net/ipv6/route.c
> index 23a20d62daac..35873b57c7f1 100644
> --- a/net/ipv6/route.c
> +++ b/net/ipv6/route.c
> @@ -111,8 +111,8 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
>  			 int iif, int type, u32 portid, u32 seq,
>  			 unsigned int flags);
>  static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
> -					   struct in6_addr *daddr,
> -					   struct in6_addr *saddr);
> +					   const struct in6_addr *daddr,
> +					   const struct in6_addr *saddr);
>  
>  #ifdef CONFIG_IPV6_ROUTE_INFO
>  static struct fib6_info *rt6_add_route_info(struct net *net,
> @@ -1566,31 +1566,44 @@ void rt6_flush_exceptions(struct fib6_info *rt)
>   * Caller has to hold rcu_read_lock()
>   */
>  static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
> -					   struct in6_addr *daddr,
> -					   struct in6_addr *saddr)
> +					   const struct in6_addr *daddr,
> +					   const struct in6_addr *saddr)
>  {
>  	struct rt6_exception_bucket *bucket;
>  	struct in6_addr *src_key = NULL;
>  	struct rt6_exception *rt6_ex;
>  	struct rt6_info *ret = NULL;
>  
> -	bucket = rcu_dereference(res->f6i->rt6i_exception_bucket);
> -
>  #ifdef CONFIG_IPV6_SUBTREES
>  	/* fib6i_src.plen != 0 indicates f6i is in subtree
>  	 * and exception table is indexed by a hash of
>  	 * both fib6_dst and fib6_src.
> -	 * Otherwise, the exception table is indexed by
> -	 * a hash of only fib6_dst.
> +	 * However, the src addr used to create the hash
> +	 * might not be exactly the passed in saddr which
> +	 * is a /128 addr from the flow.
> +	 * So we need to use f6i->fib6_src to redo lookup
> +	 * if the passed in saddr does not find anything.
> +	 * (See the logic in ip6_rt_cache_alloc() on how
> +	 * rt->rt6i_src is updated.)
>  	 */
>  	if (res->f6i->fib6_src.plen)
>  		src_key = saddr;
> +find_ex:
>  #endif
> +	bucket = rcu_dereference(res->f6i->rt6i_exception_bucket);
>  	rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
>  
>  	if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
>  		ret = rt6_ex->rt6i;
>  
> +#ifdef CONFIG_IPV6_SUBTREES
> +	/* Use fib6_src as src_key and redo lookup */
> +	if (!ret && src_key == saddr) {
I am worry about the "src_key == saddr" check.
e.g. what if "saddr == &res->f6i->fib6_src.addr" in the future.

May be "!ret && src_key && src_key != &res->f6i->fib6_src.addr"?

Other than that,
Acked-by: Martin KaFai Lau <kafai@fb.com>

Thanks for the v2.

> +		src_key = &res->f6i->fib6_src.addr;
> +		goto find_ex;
> +	}
> +#endif
> +
>  	return ret;
>  }

Re: [PATCH v2 net] ipv6: fix src addr routing with the exception table

[Wei Wang]

On Thu, May 16, 2019 at 12:15 PM Martin Lau <kafai@fb.com> wrote:
>
> On Thu, May 16, 2019 at 11:16:20AM -0700, Wei Wang wrote:
> > From: Wei Wang <weiwan@google.com>
> >
> > When inserting route cache into the exception table, the key is
> > generated with both src_addr and dest_addr with src addr routing.
> > However, current logic always assumes the src_addr used to generate the
> > key is a /128 host address. This is not true in the following scenarios:
> > 1. When the route is a gateway route or does not have next hop.
> >    (rt6_is_gw_or_nonexthop() == false)
> > 2. When calling ip6_rt_cache_alloc(), saddr is passed in as NULL.
> > This means, when looking for a route cache in the exception table, we
> > have to do the lookup twice: first time with the passed in /128 host
> > address, second time with the src_addr stored in fib6_info.
> >
> > This solves the pmtu discovery issue reported by Mikael Magnusson where
> > a route cache with a lower mtu info is created for a gateway route with
> > src addr. However, the lookup code is not able to find this route cache.
> >
> > Fixes: 2b760fcf5cfb ("ipv6: hook up exception table to store dst cache")
> > Reported-by: Mikael Magnusson <mikael.kernel@lists.m7n.se>
> > Bisected-by: David Ahern <dsahern@gmail.com>
> > Signed-off-by: Wei Wang <weiwan@google.com>
> > Cc: Martin Lau <kafai@fb.com>
> > Cc: Eric Dumazet <edumazet@google.com>
> > ---
> > Changes from v1:
> > - restructure the code to only include the new logic in
> >   rt6_find_cached_rt()
> > ---
> >  net/ipv6/route.c | 49 +++++++++++++++++++++++++-----------------------
> >  1 file changed, 26 insertions(+), 23 deletions(-)
> >
> > diff --git a/net/ipv6/route.c b/net/ipv6/route.c
> > index 23a20d62daac..35873b57c7f1 100644
> > --- a/net/ipv6/route.c
> > +++ b/net/ipv6/route.c
> > @@ -111,8 +111,8 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
> >                        int iif, int type, u32 portid, u32 seq,
> >                        unsigned int flags);
> >  static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
> > -                                        struct in6_addr *daddr,
> > -                                        struct in6_addr *saddr);
> > +                                        const struct in6_addr *daddr,
> > +                                        const struct in6_addr *saddr);
> >
> >  #ifdef CONFIG_IPV6_ROUTE_INFO
> >  static struct fib6_info *rt6_add_route_info(struct net *net,
> > @@ -1566,31 +1566,44 @@ void rt6_flush_exceptions(struct fib6_info *rt)
> >   * Caller has to hold rcu_read_lock()
> >   */
> >  static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
> > -                                        struct in6_addr *daddr,
> > -                                        struct in6_addr *saddr)
> > +                                        const struct in6_addr *daddr,
> > +                                        const struct in6_addr *saddr)
> >  {
> >       struct rt6_exception_bucket *bucket;
> >       struct in6_addr *src_key = NULL;
> >       struct rt6_exception *rt6_ex;
> >       struct rt6_info *ret = NULL;
> >
> > -     bucket = rcu_dereference(res->f6i->rt6i_exception_bucket);
> > -
> >  #ifdef CONFIG_IPV6_SUBTREES
> >       /* fib6i_src.plen != 0 indicates f6i is in subtree
> >        * and exception table is indexed by a hash of
> >        * both fib6_dst and fib6_src.
> > -      * Otherwise, the exception table is indexed by
> > -      * a hash of only fib6_dst.
> > +      * However, the src addr used to create the hash
> > +      * might not be exactly the passed in saddr which
> > +      * is a /128 addr from the flow.
> > +      * So we need to use f6i->fib6_src to redo lookup
> > +      * if the passed in saddr does not find anything.
> > +      * (See the logic in ip6_rt_cache_alloc() on how
> > +      * rt->rt6i_src is updated.)
> >        */
> >       if (res->f6i->fib6_src.plen)
> >               src_key = saddr;
> > +find_ex:
> >  #endif
> > +     bucket = rcu_dereference(res->f6i->rt6i_exception_bucket);
> >       rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
> >
> >       if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
> >               ret = rt6_ex->rt6i;
> >
> > +#ifdef CONFIG_IPV6_SUBTREES
> > +     /* Use fib6_src as src_key and redo lookup */
> > +     if (!ret && src_key == saddr) {
> I am worry about the "src_key == saddr" check.
> e.g. what if "saddr == &res->f6i->fib6_src.addr" in the future.
>
> May be "!ret && src_key && src_key != &res->f6i->fib6_src.addr"?
>
> Other than that,
> Acked-by: Martin KaFai Lau <kafai@fb.com>
>
> Thanks for the v2.
>
Hmm... That does seem to be a valid concern, although it is very
unlikely I think...
But to be safe, the check you proposed looks good to me. I will change it in v3.

> > +             src_key = &res->f6i->fib6_src.addr;
> > +             goto find_ex;
> > +     }
> > +#endif
> > +
> >       return ret;
> >  }