[PATCH net-next 0/8] net: extend RTM_GETROUTE to return fib result

[PATCH net-next 0/8] net: extend RTM_GETROUTE to return fib result

[Roopa Prabhu]

From: Roopa Prabhu <roopa@cumulusnetworks.com>

This series adds a new RTM_F_FIB_MATCH flag to return matched fib result
with RTM_GETROUTE. This is useful for applications and protocols in
userspace wanting to query the selected route.

examples (with patched iproute2):
ipv4:
----
$ip route show
default via 192.168.0.2 dev eth0
10.0.14.0/24
        nexthop via 172.16.0.3  dev dummy0 weight 1
        nexthop via 172.16.1.3  dev dummy1 weight 1

$ip route get 10.0.14.2
10.0.14.2 via 172.16.1.3 dev dummy1  src 172.16.1.1 
    cache 

$ip route get fibmatch 10.0.14.2
10.0.14.0/24
        nexthop via 172.16.0.3  dev dummy0 weight 1
        nexthop via 172.16.1.3  dev dummy1 weight 1

ipv6:
----
$ip -6 route show
2001:db9:100::/120  metric 1024 
        nexthop via 2001:db8:2::2  dev dummy0 weight 1
        nexthop via 2001:db8:12::2  dev dummy1 weight 1

$ip -6 route get 2001:db9:100::1
2001:db9:100::1 from :: via 2001:db8:12::2 dev dummy1  src 2001:db8:12::1  metric 1024  pref medium

$ip -6 route get fibmatch 2001:db9:100::1
2001:db9:100::/120  metric 1024 
        nexthop via 2001:db8:12::2  dev dummy1 weight 1
        nexthop via 2001:db8:2::2  dev dummy0 weight 1


David Ahern (5):
  net: ipv4: refactor __ip_route_output_key_hash
  net: ipv4: refactor ip_route_input_noref
  net: ipv4: Remove event arg to rt_fill_info
  net: ipv4: Convert inet_rtm_getroute to rcu versions of route lookup
  net: ipv4: Save trie prefix to fib lookup result

Roopa Prabhu (3):
  net: ipv4: add new RTM_F_FIB_MATCH flag for use with RTM_GETROUTE
  net: ipv4: RTM_GETROUTE: return matched fib result when requested
  net: ipv6: RTM_GETROUTE: return matched fib result when requested

 include/net/ip_fib.h           |   1 +
 include/net/route.h            |  10 ++-
 include/uapi/linux/rtnetlink.h |   1 +
 net/ipv4/fib_trie.c            |   1 +
 net/ipv4/icmp.c                |   2 +-
 net/ipv4/route.c               | 160 ++++++++++++++++++++++++-----------------
 net/ipv6/route.c               |  11 ++-
 7 files changed, 116 insertions(+), 70 deletions(-)

-- 
1.9.1

[PATCH net-next 1/8] net: ipv4: refactor __ip_route_output_key_hash

[Roopa Prabhu]

From: David Ahern <dsahern@gmail.com>

A later patch wants access to the fib result on an output route lookup
with the rcu lock held. Refactor __ip_route_output_key_hash, pushing
the logic between rcu_read_lock ... rcu_read_unlock into a new helper
that takes the fib_result as an input arg.

To keep the name length under control remove the leading underscores
from the name. _rcu is added to the name of the new helper indicating
it is called with the rcu read lock held.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
---
 include/net/route.h |  7 ++++++-
 net/ipv4/icmp.c     |  2 +-
 net/ipv4/route.c    | 57 +++++++++++++++++++++++++++++++----------------------
 3 files changed, 40 insertions(+), 26 deletions(-)

diff --git a/include/net/route.h b/include/net/route.h
index 2cc0e14..5a92347 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -115,11 +115,16 @@ struct rt_cache_stat {
 void rt_flush_dev(struct net_device *dev);
 struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *flp,
 					  const struct sk_buff *skb);
+struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *flp,
+					const struct sk_buff *skb);
+struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp,
+					    const struct sk_buff *skb,
+					    struct fib_result *res);
 
 static inline struct rtable *__ip_route_output_key(struct net *net,
 						   struct flowi4 *flp)
 {
-	return __ip_route_output_key_hash(net, flp, NULL);
+	return ip_route_output_key_hash(net, flp, NULL);
 }
 
 struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 43318b5..5610971 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -489,7 +489,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev);
 
 	security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
-	rt = __ip_route_output_key_hash(net, fl4, skb_in);
+	rt = ip_route_output_key_hash(net, fl4, skb_in);
 	if (IS_ERR(rt))
 		return rt;
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 655d9ee..f787208 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2246,29 +2246,22 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
  * Major route resolver routine.
  */
 
-struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
-					  const struct sk_buff *skb)
+struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
+					    const struct sk_buff *skb,
+					    struct fib_result *res)
 {
 	struct net_device *dev_out = NULL;
+	int orig_oif = fl4->flowi4_oif;
 	__u8 tos = RT_FL_TOS(fl4);
 	unsigned int flags = 0;
-	struct fib_result res;
-	struct rtable *rth;
-	int orig_oif;
 	int err = -ENETUNREACH;
-
-	res.tclassid	= 0;
-	res.fi		= NULL;
-	res.table	= NULL;
-
-	orig_oif = fl4->flowi4_oif;
+	struct rtable *rth;
 
 	fl4->flowi4_iif = LOOPBACK_IFINDEX;
 	fl4->flowi4_tos = tos & IPTOS_RT_MASK;
 	fl4->flowi4_scope = ((tos & RTO_ONLINK) ?
 			 RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
 
-	rcu_read_lock();
 	if (fl4->saddr) {
 		rth = ERR_PTR(-EINVAL);
 		if (ipv4_is_multicast(fl4->saddr) ||
@@ -2354,15 +2347,15 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
 			fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK);
 		dev_out = net->loopback_dev;
 		fl4->flowi4_oif = LOOPBACK_IFINDEX;
-		res.type = RTN_LOCAL;
+		res->type = RTN_LOCAL;
 		flags |= RTCF_LOCAL;
 		goto make_route;
 	}
 
-	err = fib_lookup(net, fl4, &res, 0);
+	err = fib_lookup(net, fl4, res, 0);
 	if (err) {
-		res.fi = NULL;
-		res.table = NULL;
+		res->fi = NULL;
+		res->table = NULL;
 		if (fl4->flowi4_oif &&
 		    (ipv4_is_multicast(fl4->daddr) ||
 		    !netif_index_is_l3_master(net, fl4->flowi4_oif))) {
@@ -2387,17 +2380,17 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
 			if (fl4->saddr == 0)
 				fl4->saddr = inet_select_addr(dev_out, 0,
 							      RT_SCOPE_LINK);
-			res.type = RTN_UNICAST;
+			res->type = RTN_UNICAST;
 			goto make_route;
 		}
 		rth = ERR_PTR(err);
 		goto out;
 	}
 
-	if (res.type == RTN_LOCAL) {
+	if (res->type == RTN_LOCAL) {
 		if (!fl4->saddr) {
-			if (res.fi->fib_prefsrc)
-				fl4->saddr = res.fi->fib_prefsrc;
+			if (res->fi->fib_prefsrc)
+				fl4->saddr = res->fi->fib_prefsrc;
 			else
 				fl4->saddr = fl4->daddr;
 		}
@@ -2410,20 +2403,36 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
 		goto make_route;
 	}
 
-	fib_select_path(net, &res, fl4, skb);
+	fib_select_path(net, res, fl4, skb);
 
-	dev_out = FIB_RES_DEV(res);
+	dev_out = FIB_RES_DEV(*res);
 	fl4->flowi4_oif = dev_out->ifindex;
 
 
 make_route:
-	rth = __mkroute_output(&res, fl4, orig_oif, dev_out, flags);
+	rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags);
 
 out:
+	return rth;
+}
+
+struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
+					const struct sk_buff *skb)
+{
+	struct fib_result res;
+	struct rtable *rth;
+
+	res.tclassid	= 0;
+	res.fi		= NULL;
+	res.table	= NULL;
+
+	rcu_read_lock();
+	rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
 	rcu_read_unlock();
+
 	return rth;
 }
-EXPORT_SYMBOL_GPL(__ip_route_output_key_hash);
+EXPORT_SYMBOL_GPL(ip_route_output_key_hash);
 
 static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
 {
-- 
1.9.1

RE: [PATCH net-next 1/8] net: ipv4: refactor __ip_route_output_key_hash

[Rosen, Rami]

Hi, Rupa /David Ahern,

First, thanks for this patch set!

Second, it seems to me that something might be incorrect here.

You have these additions in this patch  (1/8):
...
+struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp,
+					    const struct sk_buff *skb,
+					    struct fib_result *res);
...
+struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
+					const struct sk_buff *skb)
+{
+	struct fib_result res;
+	struct rtable *rth;
+
+	res.tclassid	= 0;
+	res.fi		= NULL;
+	res.table	= NULL;
+
+	rcu_read_lock();
+	rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
 	rcu_read_unlock();
+
 	return rth;
 }
-EXPORT_SYMBOL_GPL(__ip_route_output_key_hash);
+EXPORT_SYMBOL_GPL(ip_route_output_key_hash);
 

So the third parameter to ip_route_output_key_hash_rcu() should be skb*, and the fourth parameter should be fib_result *. However, you do not pass the skb parameter 
when calling ip_route_output_key_hash_rcu() in 
ip_route_output_key_hash()  (in fact you don't use it at all),  and you pass mp_hash as the fourth parameter.

Regards,
Rami Rosen
Intel Corporation

Re: [PATCH net-next 1/8] net: ipv4: refactor __ip_route_output_key_hash

[David Ahern]

On 5/24/17 1:33 PM, Rosen, Rami wrote:
> Hi, Rupa /David Ahern,
> 
> First, thanks for this patch set!
> 
> Second, it seems to me that something might be incorrect here.
> 
> You have these additions in this patch  (1/8):
> ...
> +struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp,
> +					    const struct sk_buff *skb,
> +					    struct fib_result *res);
> ...
> +struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
> +					const struct sk_buff *skb)
> +{
> +	struct fib_result res;
> +	struct rtable *rth;
> +
> +	res.tclassid	= 0;
> +	res.fi		= NULL;
> +	res.table	= NULL;
> +
> +	rcu_read_lock();
> +	rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
>  	rcu_read_unlock();
> +
>  	return rth;
>  }
> -EXPORT_SYMBOL_GPL(__ip_route_output_key_hash);
> +EXPORT_SYMBOL_GPL(ip_route_output_key_hash);
>  
> 
> So the third parameter to ip_route_output_key_hash_rcu() should be skb*, and the fourth parameter should be fib_result *. However, you do not pass the skb parameter 
> when calling ip_route_output_key_hash_rcu() in 
> ip_route_output_key_hash()  (in fact you don't use it at all),  and you pass mp_hash as the fourth parameter.

Yep, it's a problem with the forward port of the first round of patches.

Roopa: in include/net/route.h, __ip_route_output_key_hash should be
removed as well.

Re: [PATCH net-next 1/8] net: ipv4: refactor __ip_route_output_key_hash

[Roopa Prabhu]

On Wed, May 24, 2017 at 6:10 PM, David Ahern <dsahern@gmail.com> wrote:
> On 5/24/17 1:33 PM, Rosen, Rami wrote:
>> Hi, Rupa /David Ahern,
>>
>> First, thanks for this patch set!
>>
>> Second, it seems to me that something might be incorrect here.
>>
>> You have these additions in this patch  (1/8):
>> ...
>> +struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp,
>> +                                         const struct sk_buff *skb,
>> +                                         struct fib_result *res);
>> ...
>> +struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
>> +                                     const struct sk_buff *skb)
>> +{
>> +     struct fib_result res;
>> +     struct rtable *rth;
>> +
>> +     res.tclassid    = 0;
>> +     res.fi          = NULL;
>> +     res.table       = NULL;
>> +
>> +     rcu_read_lock();
>> +     rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
>>       rcu_read_unlock();
>> +
>>       return rth;
>>  }
>> -EXPORT_SYMBOL_GPL(__ip_route_output_key_hash);
>> +EXPORT_SYMBOL_GPL(ip_route_output_key_hash);
>>
>>
>> So the third parameter to ip_route_output_key_hash_rcu() should be skb*, and the fourth parameter should be fib_result *. However, you do not pass the skb parameter
>> when calling ip_route_output_key_hash_rcu() in
>> ip_route_output_key_hash()  (in fact you don't use it at all),  and you pass mp_hash as the fourth parameter.
>
> Yep, it's a problem with the forward port of the first round of patches.

yep,

>
> Roopa: in include/net/route.h, __ip_route_output_key_hash should be
> removed as well.

ack, thanks Rami and david.

will fix it in v2.

Re: [PATCH net-next 1/8] net: ipv4: refactor __ip_route_output_key_hash

[kbuild test robot]

[-- Attachment #1: Type: text/plain, Size: 5778 bytes --]

Hi David,

[auto build test ERROR on net-next/master]

url:    https://github.com/0day-ci/linux/commits/Roopa-Prabhu/net-extend-RTM_GETROUTE-to-return-fib-result/20170525-053253
config: cris-etrax-100lx_v2_defconfig (attached as .config)
compiler: cris-linux-gcc (GCC) 6.2.0
reproduce:
        wget https://raw.githubusercontent.com/01org/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        make.cross ARCH=cris 

Note: the linux-review/Roopa-Prabhu/net-extend-RTM_GETROUTE-to-return-fib-result/20170525-053253 HEAD 083c4ee9e124d0acf29d159ced8a22cb41665a7a builds fine.
      It only hurts bisectibility.

All error/warnings (new ones prefixed by >>):

   In file included from include/net/route.h:31:0,
                    from include/net/lwtunnel.h:8,
                    from include/net/ip_tunnels.h:17,
                    from include/net/dst_metadata.h:5,
                    from net/ipv4/route.c:94:
   net/ipv4/route.c: In function 'ip_route_output_key_hash_rcu':
>> include/net/ip_fib.h:167:32: error: 'res' is a pointer; did you mean to use '->'?
    #define FIB_RES_NH(res)  ((res).fi->fib_nh[0])
                                   ^
                                      ->
>> include/net/ip_fib.h:196:28: note: in expansion of macro 'FIB_RES_NH'
    #define FIB_RES_DEV(res)  (FIB_RES_NH(res).nh_dev)
                               ^~~~~~~~~~
>> net/ipv4/route.c:2399:35: note: in expansion of macro 'FIB_RES_DEV'
      dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? :
                                      ^~~~~~~~~~~
   net/ipv4/route.c: In function 'ip_route_output_key_hash':
>> net/ipv4/route.c:2430:53: error: 'mp_hash' undeclared (first use in this function)
     rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
                                                        ^~~~~~~
   net/ipv4/route.c:2430:53: note: each undeclared identifier is reported only once for each function it appears in
>> net/ipv4/route.c:2430:47: error: passing argument 3 of 'ip_route_output_key_hash_rcu' from incompatible pointer type [-Werror=incompatible-pointer-types]
     rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
                                                  ^
   net/ipv4/route.c:2249:16: note: expected 'const struct sk_buff *' but argument is of type 'struct fib_result *'
    struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
                   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
   cc1: some warnings being treated as errors
--
   In file included from include/net/route.h:31:0,
                    from include/net/lwtunnel.h:8,
                    from include/net/ip_tunnels.h:17,
                    from include/net/dst_metadata.h:5,
                    from net//ipv4/route.c:94:
   net//ipv4/route.c: In function 'ip_route_output_key_hash_rcu':
>> include/net/ip_fib.h:167:32: error: 'res' is a pointer; did you mean to use '->'?
    #define FIB_RES_NH(res)  ((res).fi->fib_nh[0])
                                   ^
                                      ->
>> include/net/ip_fib.h:196:28: note: in expansion of macro 'FIB_RES_NH'
    #define FIB_RES_DEV(res)  (FIB_RES_NH(res).nh_dev)
                               ^~~~~~~~~~
   net//ipv4/route.c:2399:35: note: in expansion of macro 'FIB_RES_DEV'
      dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? :
                                      ^~~~~~~~~~~
   net//ipv4/route.c: In function 'ip_route_output_key_hash':
   net//ipv4/route.c:2430:53: error: 'mp_hash' undeclared (first use in this function)
     rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
                                                        ^~~~~~~
   net//ipv4/route.c:2430:53: note: each undeclared identifier is reported only once for each function it appears in
   net//ipv4/route.c:2430:47: error: passing argument 3 of 'ip_route_output_key_hash_rcu' from incompatible pointer type [-Werror=incompatible-pointer-types]
     rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
                                                  ^
   net//ipv4/route.c:2249:16: note: expected 'const struct sk_buff *' but argument is of type 'struct fib_result *'
    struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
                   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
   cc1: some warnings being treated as errors

vim +/mp_hash +2430 net/ipv4/route.c

  2393					fl4->saddr = res->fi->fib_prefsrc;
  2394				else
  2395					fl4->saddr = fl4->daddr;
  2396			}
  2397	
  2398			/* L3 master device is the loopback for that domain */
> 2399			dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? :
  2400				net->loopback_dev;
  2401			fl4->flowi4_oif = dev_out->ifindex;
  2402			flags |= RTCF_LOCAL;
  2403			goto make_route;
  2404		}
  2405	
  2406		fib_select_path(net, res, fl4, skb);
  2407	
  2408		dev_out = FIB_RES_DEV(*res);
  2409		fl4->flowi4_oif = dev_out->ifindex;
  2410	
  2411	
  2412	make_route:
  2413		rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags);
  2414	
  2415	out:
  2416		return rth;
  2417	}
  2418	
  2419	struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
  2420						const struct sk_buff *skb)
  2421	{
  2422		struct fib_result res;
  2423		struct rtable *rth;
  2424	
  2425		res.tclassid	= 0;
  2426		res.fi		= NULL;
  2427		res.table	= NULL;
  2428	
  2429		rcu_read_lock();
> 2430		rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
  2431		rcu_read_unlock();
  2432	
  2433		return rth;

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation

[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 8682 bytes --]

Re: [PATCH net-next 1/8] net: ipv4: refactor __ip_route_output_key_hash

[kbuild test robot]

[-- Attachment #1: Type: text/plain, Size: 6359 bytes --]

Hi David,

[auto build test ERROR on net-next/master]

url:    https://github.com/0day-ci/linux/commits/Roopa-Prabhu/net-extend-RTM_GETROUTE-to-return-fib-result/20170525-053253
config: openrisc-or1ksim_defconfig (attached as .config)
compiler: or1k-linux-gcc (GCC) 5.4.0
reproduce:
        wget https://raw.githubusercontent.com/01org/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        make.cross ARCH=openrisc 

Note: the linux-review/Roopa-Prabhu/net-extend-RTM_GETROUTE-to-return-fib-result/20170525-053253 HEAD 083c4ee9e124d0acf29d159ced8a22cb41665a7a builds fine.
      It only hurts bisectibility.

All errors (new ones prefixed by >>):

   In file included from include/net/route.h:31:0,
                    from include/net/lwtunnel.h:8,
                    from include/net/ip_tunnels.h:17,
                    from include/net/dst_metadata.h:5,
                    from net/ipv4/route.c:94:
   net/ipv4/route.c: In function 'ip_route_output_key_hash_rcu':
>> include/net/ip_fib.h:167:32: error: request for member 'fi' in something not a structure or union
    #define FIB_RES_NH(res)  ((res).fi->fib_nh[0])
                                   ^
   include/net/ip_fib.h:196:28: note: in expansion of macro 'FIB_RES_NH'
    #define FIB_RES_DEV(res)  (FIB_RES_NH(res).nh_dev)
                               ^
   net/ipv4/route.c:2399:35: note: in expansion of macro 'FIB_RES_DEV'
      dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? :
                                      ^
   net/ipv4/route.c: In function 'ip_route_output_key_hash':
   net/ipv4/route.c:2430:53: error: 'mp_hash' undeclared (first use in this function)
     rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
                                                        ^
   net/ipv4/route.c:2430:53: note: each undeclared identifier is reported only once for each function it appears in
   net/ipv4/route.c:2430:47: error: passing argument 3 of 'ip_route_output_key_hash_rcu' from incompatible pointer type [-Werror=incompatible-pointer-types]
     rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
                                                  ^
   net/ipv4/route.c:2249:16: note: expected 'const struct sk_buff *' but argument is of type 'struct fib_result *'
    struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
                   ^
   cc1: some warnings being treated as errors
--
   In file included from include/net/route.h:31:0,
                    from include/net/lwtunnel.h:8,
                    from include/net/ip_tunnels.h:17,
                    from include/net/dst_metadata.h:5,
                    from net//ipv4/route.c:94:
   net//ipv4/route.c: In function 'ip_route_output_key_hash_rcu':
>> include/net/ip_fib.h:167:32: error: request for member 'fi' in something not a structure or union
    #define FIB_RES_NH(res)  ((res).fi->fib_nh[0])
                                   ^
   include/net/ip_fib.h:196:28: note: in expansion of macro 'FIB_RES_NH'
    #define FIB_RES_DEV(res)  (FIB_RES_NH(res).nh_dev)
                               ^
   net//ipv4/route.c:2399:35: note: in expansion of macro 'FIB_RES_DEV'
      dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? :
                                      ^
   net//ipv4/route.c: In function 'ip_route_output_key_hash':
   net//ipv4/route.c:2430:53: error: 'mp_hash' undeclared (first use in this function)
     rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
                                                        ^
   net//ipv4/route.c:2430:53: note: each undeclared identifier is reported only once for each function it appears in
   net//ipv4/route.c:2430:47: error: passing argument 3 of 'ip_route_output_key_hash_rcu' from incompatible pointer type [-Werror=incompatible-pointer-types]
     rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
                                                  ^
   net//ipv4/route.c:2249:16: note: expected 'const struct sk_buff *' but argument is of type 'struct fib_result *'
    struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
                   ^
   cc1: some warnings being treated as errors

vim +/fi +167 include/net/ip_fib.h

5f300893f Thomas Graf    2006-11-09  151  	u32		fl_mark;
246955fe4 Robert Olsson  2005-06-20  152  	unsigned char	fl_tos;
246955fe4 Robert Olsson  2005-06-20  153  	unsigned char   fl_scope;
246955fe4 Robert Olsson  2005-06-20  154  	unsigned char   tb_id_in;
246955fe4 Robert Olsson  2005-06-20  155  
246955fe4 Robert Olsson  2005-06-20  156  	unsigned char   tb_id;      /* Results */
246955fe4 Robert Olsson  2005-06-20  157  	unsigned char	prefixlen;
246955fe4 Robert Olsson  2005-06-20  158  	unsigned char	nh_sel;
246955fe4 Robert Olsson  2005-06-20  159  	unsigned char	type;
246955fe4 Robert Olsson  2005-06-20  160  	unsigned char	scope;
246955fe4 Robert Olsson  2005-06-20  161  	int             err;      
246955fe4 Robert Olsson  2005-06-20  162  };
^1da177e4 Linus Torvalds 2005-04-16  163  
^1da177e4 Linus Torvalds 2005-04-16  164  #ifdef CONFIG_IP_ROUTE_MULTIPATH
^1da177e4 Linus Torvalds 2005-04-16  165  #define FIB_RES_NH(res)		((res).fi->fib_nh[(res).nh_sel])
^1da177e4 Linus Torvalds 2005-04-16  166  #else /* CONFIG_IP_ROUTE_MULTIPATH */
^1da177e4 Linus Torvalds 2005-04-16 @167  #define FIB_RES_NH(res)		((res).fi->fib_nh[0])
5b9e12dbf Denis V. Lunev 2013-03-13  168  #endif /* CONFIG_IP_ROUTE_MULTIPATH */
^1da177e4 Linus Torvalds 2005-04-16  169  
5b9e12dbf Denis V. Lunev 2013-03-13  170  #ifdef CONFIG_IP_MULTIPLE_TABLES
93456b6d7 Denis V. Lunev 2008-01-10  171  #define FIB_TABLE_HASHSZ 256
5b9e12dbf Denis V. Lunev 2013-03-13  172  #else
5b9e12dbf Denis V. Lunev 2013-03-13  173  #define FIB_TABLE_HASHSZ 2
5b9e12dbf Denis V. Lunev 2013-03-13  174  #endif
^1da177e4 Linus Torvalds 2005-04-16  175  

:::::: The code at line 167 was first introduced by commit
:::::: 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 Linux-2.6.12-rc2

:::::: TO: Linus Torvalds <torvalds@ppc970.osdl.org>
:::::: CC: Linus Torvalds <torvalds@ppc970.osdl.org>

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation

[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 7551 bytes --]

[PATCH net-next 2/8] net: ipv4: refactor ip_route_input_noref

[Roopa Prabhu]

From: David Ahern <dsahern@gmail.com>

A later patch wants access to the fib result on an input route lookup
with the rcu lock held. Refactor ip_route_input_noref pushing the logic
between rcu_read_lock ... rcu_read_unlock into a new helper that takes
the fib_result as an input arg.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
---
 include/net/route.h |  3 +++
 net/ipv4/route.c    | 66 ++++++++++++++++++++++++++++++-----------------------
 2 files changed, 40 insertions(+), 29 deletions(-)

diff --git a/include/net/route.h b/include/net/route.h
index 5a92347..8d209ad 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -180,6 +180,9 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4
 
 int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
 			 u8 tos, struct net_device *devin);
+int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src,
+		       u8 tos, struct net_device *devin,
+		       struct fib_result *res);
 
 static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
 				 u8 tos, struct net_device *devin)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f787208..fe7b765 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1852,9 +1852,9 @@ static int ip_mkroute_input(struct sk_buff *skb,
  */
 
 static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
-			       u8 tos, struct net_device *dev)
+			       u8 tos, struct net_device *dev,
+			       struct fib_result *res)
 {
-	struct fib_result res;
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
 	struct ip_tunnel_info *tun_info;
 	struct flowi4	fl4;
@@ -1884,8 +1884,8 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr))
 		goto martian_source;
 
-	res.fi = NULL;
-	res.table = NULL;
+	res->fi = NULL;
+	res->table = NULL;
 	if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0))
 		goto brd_input;
 
@@ -1921,17 +1921,17 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
 	fl4.flowi4_uid = sock_net_uid(net, NULL);
-	err = fib_lookup(net, &fl4, &res, 0);
+	err = fib_lookup(net, &fl4, res, 0);
 	if (err != 0) {
 		if (!IN_DEV_FORWARD(in_dev))
 			err = -EHOSTUNREACH;
 		goto no_route;
 	}
 
-	if (res.type == RTN_BROADCAST)
+	if (res->type == RTN_BROADCAST)
 		goto brd_input;
 
-	if (res.type == RTN_LOCAL) {
+	if (res->type == RTN_LOCAL) {
 		err = fib_validate_source(skb, saddr, daddr, tos,
 					  0, dev, in_dev, &itag);
 		if (err < 0)
@@ -1943,10 +1943,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		err = -EHOSTUNREACH;
 		goto no_route;
 	}
-	if (res.type != RTN_UNICAST)
+	if (res->type != RTN_UNICAST)
 		goto martian_destination;
 
-	err = ip_mkroute_input(skb, &res, in_dev, daddr, saddr, tos);
+	err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos);
 out:	return err;
 
 brd_input:
@@ -1960,14 +1960,14 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 			goto martian_source;
 	}
 	flags |= RTCF_BROADCAST;
-	res.type = RTN_BROADCAST;
+	res->type = RTN_BROADCAST;
 	RT_CACHE_STAT_INC(in_brd);
 
 local_input:
 	do_cache = false;
-	if (res.fi) {
+	if (res->fi) {
 		if (!itag) {
-			rth = rcu_dereference(FIB_RES_NH(res).nh_rth_input);
+			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
 			if (rt_cache_valid(rth)) {
 				skb_dst_set_noref(skb, &rth->dst);
 				err = 0;
@@ -1978,7 +1978,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	}
 
 	rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev,
-			   flags | RTCF_LOCAL, res.type,
+			   flags | RTCF_LOCAL, res->type,
 			   IN_DEV_CONF_GET(in_dev, NOPOLICY), false, do_cache);
 	if (!rth)
 		goto e_nobufs;
@@ -1988,18 +1988,18 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	rth->dst.tclassid = itag;
 #endif
 	rth->rt_is_input = 1;
-	if (res.table)
-		rth->rt_table_id = res.table->tb_id;
+	if (res->table)
+		rth->rt_table_id = res->table->tb_id;
 
 	RT_CACHE_STAT_INC(in_slow_tot);
-	if (res.type == RTN_UNREACHABLE) {
+	if (res->type == RTN_UNREACHABLE) {
 		rth->dst.input= ip_error;
 		rth->dst.error= -err;
 		rth->rt_flags 	&= ~RTCF_LOCAL;
 	}
 
 	if (do_cache) {
-		struct fib_nh *nh = &FIB_RES_NH(res);
+		struct fib_nh *nh = &FIB_RES_NH(*res);
 
 		rth->dst.lwtstate = lwtstate_get(nh->nh_lwtstate);
 		if (lwtunnel_input_redirect(rth->dst.lwtstate)) {
@@ -2019,9 +2019,9 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 
 no_route:
 	RT_CACHE_STAT_INC(in_no_route);
-	res.type = RTN_UNREACHABLE;
-	res.fi = NULL;
-	res.table = NULL;
+	res->type = RTN_UNREACHABLE;
+	res->fi = NULL;
+	res->table = NULL;
 	goto local_input;
 
 	/*
@@ -2051,11 +2051,22 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 			 u8 tos, struct net_device *dev)
 {
-	int res;
+	struct fib_result res;
+	int err;
 
 	tos &= IPTOS_RT_MASK;
 	rcu_read_lock();
+	err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res);
+	rcu_read_unlock();
 
+	return err;
+}
+EXPORT_SYMBOL(ip_route_input_noref);
+
+/* called with rcu_read_lock held */
+int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+		       u8 tos, struct net_device *dev, struct fib_result *res)
+{
 	/* Multicast recognition logic is moved from route cache to here.
 	   The problem was that too many Ethernet cards have broken/missing
 	   hardware multicast filters :-( As result the host on multicasting
@@ -2070,6 +2081,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (ipv4_is_multicast(daddr)) {
 		struct in_device *in_dev = __in_dev_get_rcu(dev);
 		int our = 0;
+		int err = -EINVAL;
 
 		if (in_dev)
 			our = ip_check_mc_rcu(in_dev, daddr, saddr,
@@ -2085,7 +2097,6 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 						      ip_hdr(skb)->protocol);
 		}
 
-		res = -EINVAL;
 		if (our
 #ifdef CONFIG_IP_MROUTE
 			||
@@ -2093,17 +2104,14 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		     IN_DEV_MFORWARD(in_dev))
 #endif
 		   ) {
-			res = ip_route_input_mc(skb, daddr, saddr,
+			err = ip_route_input_mc(skb, daddr, saddr,
 						tos, dev, our);
 		}
-		rcu_read_unlock();
-		return res;
+		return err;
 	}
-	res = ip_route_input_slow(skb, daddr, saddr, tos, dev);
-	rcu_read_unlock();
-	return res;
+
+	return ip_route_input_slow(skb, daddr, saddr, tos, dev, res);
 }
-EXPORT_SYMBOL(ip_route_input_noref);
 
 /* called with rcu_read_lock() */
 static struct rtable *__mkroute_output(const struct fib_result *res,
-- 
1.9.1

[PATCH net-next 3/8] net: ipv4: Remove event arg to rt_fill_info

[Roopa Prabhu]

From: David Ahern <dsahern@gmail.com>

rt_fill_info has 1 caller with the event set to RTM_NEWROUTE. Given that
remove the arg and use RTM_NEWROUTE directly in rt_fill_info.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
---
 net/ipv4/route.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index fe7b765..9699e9b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2536,7 +2536,7 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
 
 static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
 			struct flowi4 *fl4, struct sk_buff *skb, u32 portid,
-			u32 seq, int event)
+			u32 seq)
 {
 	struct rtable *rt = skb_rtable(skb);
 	struct rtmsg *r;
@@ -2545,7 +2545,7 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
 	u32 error;
 	u32 metrics[RTAX_MAX];
 
-	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*r), 0);
+	nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), 0);
 	if (!nlh)
 		return -EMSGSIZE;
 
@@ -2745,8 +2745,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		table_id = rt->rt_table_id;
 
 	err = rt_fill_info(net, dst, src, table_id, &fl4, skb,
-			   NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
-			   RTM_NEWROUTE);
+			   NETLINK_CB(in_skb).portid, nlh->nlmsg_seq);
 	if (err < 0)
 		goto errout_free;
 
-- 
1.9.1

[PATCH net-next 4/8] net: ipv4: Convert inet_rtm_getroute to rcu versions of route lookup

[Roopa Prabhu]

From: David Ahern <dsahern@gmail.com>

Convert inet_rtm_getroute to use ip_route_input_rcu and
ip_route_output_key_hash_rcu passing the fib_result arg to both.
The rcu lock is held through the creation of the response, so the
rtable/dst does not need to be attached to the skb and is passed
to rt_fill_info directly.

In converting from ip_route_output_key to ip_route_output_key_hash_rcu
the xfrm_lookup_route in ip_route_output_flow is dropped since
flowi4_proto is not set for a route get request.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
---
 net/ipv4/route.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 9699e9b..6e0bd40 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2404,7 +2404,7 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
 		}
 
 		/* L3 master device is the loopback for that domain */
-		dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? :
+		dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) ? :
 			net->loopback_dev;
 		fl4->flowi4_oif = dev_out->ifindex;
 		flags |= RTCF_LOCAL;
@@ -2435,7 +2435,7 @@ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
 	res.table	= NULL;
 
 	rcu_read_lock();
-	rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
+	rth = ip_route_output_key_hash_rcu(net, fl4, skb, &res);
 	rcu_read_unlock();
 
 	return rth;
@@ -2534,11 +2534,11 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
 }
 EXPORT_SYMBOL_GPL(ip_route_output_flow);
 
+/* called with rcu_read_lock held */
 static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
 			struct flowi4 *fl4, struct sk_buff *skb, u32 portid,
-			u32 seq)
+			u32 seq, struct rtable *rt)
 {
-	struct rtable *rt = skb_rtable(skb);
 	struct rtmsg *r;
 	struct nlmsghdr *nlh;
 	unsigned long expires = 0;
@@ -2653,6 +2653,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	struct net *net = sock_net(in_skb->sk);
 	struct rtmsg *rtm;
 	struct nlattr *tb[RTA_MAX+1];
+	struct fib_result res = {};
 	struct rtable *rt = NULL;
 	struct flowi4 fl4;
 	__be32 dst = 0;
@@ -2709,10 +2710,12 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	fl4.flowi4_mark = mark;
 	fl4.flowi4_uid = uid;
 
+	rcu_read_lock();
+
 	if (iif) {
 		struct net_device *dev;
 
-		dev = __dev_get_by_index(net, iif);
+		dev = dev_get_by_index_rcu(net, iif);
 		if (!dev) {
 			err = -ENODEV;
 			goto errout_free;
@@ -2721,14 +2724,14 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		skb->protocol	= htons(ETH_P_IP);
 		skb->dev	= dev;
 		skb->mark	= mark;
-		err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev);
+		err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos,
+					 dev, &res);
 
 		rt = skb_rtable(skb);
 		if (err == 0 && rt->dst.error)
 			err = -rt->dst.error;
 	} else {
-		rt = ip_route_output_key(net, &fl4);
-
+		rt = ip_route_output_key_hash_rcu(net, &fl4, skb, &res);
 		err = 0;
 		if (IS_ERR(rt))
 			err = PTR_ERR(rt);
@@ -2737,7 +2740,6 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	if (err)
 		goto errout_free;
 
-	skb_dst_set(skb, &rt->dst);
 	if (rtm->rtm_flags & RTM_F_NOTIFY)
 		rt->rt_flags |= RTCF_NOTIFY;
 
@@ -2745,15 +2747,18 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		table_id = rt->rt_table_id;
 
 	err = rt_fill_info(net, dst, src, table_id, &fl4, skb,
-			   NETLINK_CB(in_skb).portid, nlh->nlmsg_seq);
+			   NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, rt);
 	if (err < 0)
 		goto errout_free;
 
+	rcu_read_unlock();
+
 	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
 errout:
 	return err;
 
 errout_free:
+	rcu_read_unlock();
 	kfree_skb(skb);
 	goto errout;
 }
-- 
1.9.1

[PATCH net-next 5/8] net: ipv4: Save trie prefix to fib lookup result

[Roopa Prabhu]

From: David Ahern <dsahern@gmail.com>

Prefix is needed for returning matching route spec on get route request.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
---
 include/net/ip_fib.h | 1 +
 net/ipv4/fib_trie.c  | 1 +
 2 files changed, 2 insertions(+)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 42e8b8f..25f5c51 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -136,6 +136,7 @@ struct fib_info {
 
 struct fib_table;
 struct fib_result {
+	__be32		prefix;
 	unsigned char	prefixlen;
 	unsigned char	nh_sel;
 	unsigned char	type;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 6d0f6c79..6e9df7d 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1452,6 +1452,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
 			if (!(fib_flags & FIB_LOOKUP_NOREF))
 				atomic_inc(&fi->fib_clntref);
 
+			res->prefix = htonl(n->key);
 			res->prefixlen = KEYLENGTH - fa->fa_slen;
 			res->nh_sel = nhsel;
 			res->type = fa->fa_type;
-- 
1.9.1

[PATCH net-next 6/8] net: ipv4: add new RTM_F_FIB_MATCH flag for use with RTM_GETROUTE

[Roopa Prabhu]

From: Roopa Prabhu <roopa@cumulusnetworks.com>

This flag when specified will return matched fib result in
response to a RTM_GETROUTE query.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
---
 include/uapi/linux/rtnetlink.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 6487b21..564790e 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -278,6 +278,7 @@ enum rt_scope_t {
 #define RTM_F_EQUALIZE		0x400	/* Multipath equalizer: NI	*/
 #define RTM_F_PREFIX		0x800	/* Prefix addresses		*/
 #define RTM_F_LOOKUP_TABLE	0x1000	/* set rtm_table to FIB lookup result */
+#define RTM_F_FIB_MATCH	        0x2000	/* return full fib lookup match */
 
 /* Reserved table identifiers */
 
-- 
1.9.1

[PATCH net-next 7/8] net: ipv4: RTM_GETROUTE: return matched fib result when requested

[Roopa Prabhu]

From: Roopa Prabhu <roopa@cumulusnetworks.com>

This patch adds support to return matched fib result when RTM_F_FIB_MATCH
flag is specified in RTM_GETROUTE request. This is useful for user-space
applications/controllers wanting to query a matching route.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
---
 net/ipv4/route.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6e0bd40..419bdba 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -114,6 +114,8 @@
 #include <net/ip_tunnels.h>
 #include <net/l3mdev.h>
 
+#include "fib_lookup.h"
+
 #define RT_FL_TOS(oldflp4) \
 	((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
 
@@ -2746,8 +2748,15 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE)
 		table_id = rt->rt_table_id;
 
-	err = rt_fill_info(net, dst, src, table_id, &fl4, skb,
-			   NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, rt);
+	if (rtm->rtm_flags & RTM_F_FIB_MATCH)
+		err = fib_dump_info(skb, NETLINK_CB(in_skb).portid,
+				    nlh->nlmsg_seq, RTM_NEWROUTE, table_id,
+				    rt->rt_type, res.prefix, res.prefixlen,
+				    fl4.flowi4_tos, res.fi, 0);
+	else
+		err = rt_fill_info(net, dst, src, table_id, &fl4, skb,
+				   NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
+				   rt);
 	if (err < 0)
 		goto errout_free;
 
-- 
1.9.1

Re: [PATCH net-next 7/8] net: ipv4: RTM_GETROUTE: return matched fib result when requested

[David Ahern]

On 5/24/17 12:19 PM, Roopa Prabhu wrote:

> @@ -2746,8 +2748,15 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
>  	if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE)
>  		table_id = rt->rt_table_id;
>  
> -	err = rt_fill_info(net, dst, src, table_id, &fl4, skb,
> -			   NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, rt);
> +	if (rtm->rtm_flags & RTM_F_FIB_MATCH)
> +		err = fib_dump_info(skb, NETLINK_CB(in_skb).portid,
> +				    nlh->nlmsg_seq, RTM_NEWROUTE, table_id,
> +				    rt->rt_type, res.prefix, res.prefixlen,
> +				    fl4.flowi4_tos, res.fi, 0);

I like this part -- much simpler than duplicating the attributes which
is where I was headed.

[PATCH net-next 8/8] net: ipv6: RTM_GETROUTE: return matched fib result when requested

[Roopa Prabhu]

From: Roopa Prabhu <roopa@cumulusnetworks.com>

This patch adds support to return matched fib result when RTM_F_FIB_MATCH
flag is specified in RTM_GETROUTE request. This is useful for user-space
applications/controllers wanting to query a matching route.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
---
 net/ipv6/route.c | 36 +++++++++++++++++++++++++++++-------
 1 file changed, 29 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 80bda31..c4d6da9 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3612,6 +3612,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	struct rtmsg *rtm;
 	struct flowi6 fl6;
 	int err, iif = 0, oif = 0;
+	bool fibmatch;
 
 	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy,
 			  extack);
@@ -3622,6 +3623,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	memset(&fl6, 0, sizeof(fl6));
 	rtm = nlmsg_data(nlh);
 	fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0);
+	fibmatch = (rtm->rtm_flags & RTM_F_FIB_MATCH) ? true : false;
 
 	if (tb[RTA_SRC]) {
 		if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
@@ -3667,12 +3669,27 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		if (!ipv6_addr_any(&fl6.saddr))
 			flags |= RT6_LOOKUP_F_HAS_SADDR;
 
-		rt = (struct rt6_info *)ip6_route_input_lookup(net, dev, &fl6,
-							       flags);
+		if (!fibmatch)
+			rt = (struct rt6_info *)ip6_route_input_lookup(net, dev,
+								       &fl6,
+								       flags);
 	} else {
 		fl6.flowi6_oif = oif;
 
-		rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
+		if (!fibmatch)
+			rt = (struct rt6_info *)ip6_route_output_flags(net,
+								       NULL,
+								       &fl6, 0);
+	}
+
+	if (fibmatch) {
+		rt = (struct rt6_info *)ip6_route_lookup(net, &fl6, 0);
+		if (rt->dst.error) {
+			err = rt->dst.error;
+			ip6_rt_put(rt);
+			goto errout;
+		}
+
 	}
 
 	if (rt == net->ipv6.ip6_null_entry) {
@@ -3689,10 +3706,15 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	}
 
 	skb_dst_set(skb, &rt->dst);
-
-	err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif,
-			    RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
-			    nlh->nlmsg_seq, 0);
+	if (fibmatch) {
+		err = rt6_fill_node(net, skb, rt, NULL, NULL, iif,
+				    RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
+				    nlh->nlmsg_seq, 0);
+	} else {
+		err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif,
+				    RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
+				    nlh->nlmsg_seq, 0);
+	}
 	if (err < 0) {
 		kfree_skb(skb);
 		goto errout;
-- 
1.9.1

Re: [PATCH net-next 8/8] net: ipv6: RTM_GETROUTE: return matched fib result when requested

[David Ahern]

Since you have to do a v2 ...

On 5/24/17 12:19 PM, Roopa Prabhu wrote:
> @@ -3622,6 +3623,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
>  	memset(&fl6, 0, sizeof(fl6));
>  	rtm = nlmsg_data(nlh);
>  	fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0);
> +	fibmatch = (rtm->rtm_flags & RTM_F_FIB_MATCH) ? true : false;
this is typically done as !!(rtm->rtm_flags & RTM_F_FIB_MATCH)
>  
>  	if (tb[RTA_SRC]) {
>  		if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
> @@ -3667,12 +3669,27 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
>  		if (!ipv6_addr_any(&fl6.saddr))
>  			flags |= RT6_LOOKUP_F_HAS_SADDR;
>  
> -		rt = (struct rt6_info *)ip6_route_input_lookup(net, dev, &fl6,
> -							       flags);
> +		if (!fibmatch)
> +			rt = (struct rt6_info *)ip6_route_input_lookup(net, dev,
> +								       &fl6,
> +								       flags);
>  	} else {
>  		fl6.flowi6_oif = oif;
>  
> -		rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
> +		if (!fibmatch)
> +			rt = (struct rt6_info *)ip6_route_output_flags(net,
> +								       NULL,
> +								       &fl6, 0);
> +	}
> +
> +	if (fibmatch) {
> +		rt = (struct rt6_info *)ip6_route_lookup(net, &fl6, 0);
> +		if (rt->dst.error) {
> +			err = rt->dst.error;
> +			ip6_rt_put(rt);
> +			goto errout;
> +		}
> +

I'd prefer to see the typecasts go away and use container_of to go from
dst_entry to rt6_info. I realize some of this is movement of existing
code, but better to clean up as we go.

Re: [PATCH net-next 8/8] net: ipv6: RTM_GETROUTE: return matched fib result when requested

[Roopa Prabhu]

On Wed, May 24, 2017 at 7:35 PM, David Ahern <dsahern@gmail.com> wrote:
> Since you have to do a v2 ...
>
> On 5/24/17 12:19 PM, Roopa Prabhu wrote:
>> @@ -3622,6 +3623,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
>>       memset(&fl6, 0, sizeof(fl6));
>>       rtm = nlmsg_data(nlh);
>>       fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0);
>> +     fibmatch = (rtm->rtm_flags & RTM_F_FIB_MATCH) ? true : false;
> this is typically done as !!(rtm->rtm_flags & RTM_F_FIB_MATCH)

ack,


>>
>>       if (tb[RTA_SRC]) {
>>               if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
>> @@ -3667,12 +3669,27 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
>>               if (!ipv6_addr_any(&fl6.saddr))
>>                       flags |= RT6_LOOKUP_F_HAS_SADDR;
>>
>> -             rt = (struct rt6_info *)ip6_route_input_lookup(net, dev, &fl6,
>> -                                                            flags);
>> +             if (!fibmatch)
>> +                     rt = (struct rt6_info *)ip6_route_input_lookup(net, dev,
>> +                                                                    &fl6,
>> +                                                                    flags);
>>       } else {
>>               fl6.flowi6_oif = oif;
>>
>> -             rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
>> +             if (!fibmatch)
>> +                     rt = (struct rt6_info *)ip6_route_output_flags(net,
>> +                                                                    NULL,
>> +                                                                    &fl6, 0);
>> +     }
>> +
>> +     if (fibmatch) {
>> +             rt = (struct rt6_info *)ip6_route_lookup(net, &fl6, 0);
>> +             if (rt->dst.error) {
>> +                     err = rt->dst.error;
>> +                     ip6_rt_put(rt);
>> +                     goto errout;
>> +             }
>> +
>
> I'd prefer to see the typecasts go away and use container_of to go from
> dst_entry to rt6_info. I realize some of this is movement of existing
> code, but better to clean up as we go.
>

ack. But that is pretty much all of ipv6 code. so, seems better done
with an incremental cleanup patch.


thanks for the review.

Re: [PATCH net-next 8/8] net: ipv6: RTM_GETROUTE: return matched fib result when requested

[David Ahern]

> On May 25, 2017, at 9:54 AM, Roopa Prabhu <roopa@cumulusnetworks.com> wrote:
> 
>> 
>> I'd prefer to see the typecasts go away and use container_of to go from
>> dst_entry to rt6_info. I realize some of this is movement of existing
>> code, but better to clean up as we go.
>> 
> 
> ack. But that is pretty much all of ipv6 code. so, seems better done
> with an incremental cleanup patch.
> 

For the rest of the ipv6 code, yes. We can do the right thing now for new code and changes to existing code.