netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: David Ahern <dsa@cumulusnetworks.com>
To: netdev@vger.kernel.org
Cc: David Ahern <dsa@cumulusnetworks.com>
Subject: [PATCH v2 net-next] net: ipv6: Use passed in table for nexthop lookups
Date: Sun, 24 Apr 2016 21:26:04 -0700	[thread overview]
Message-ID: <1461558364-17970-1-git-send-email-dsa@cumulusnetworks.com> (raw)

Similar to 3bfd847203c6 ("net: Use passed in table for nexthop lookups")
for IPv4, if the route spec contains a table id use that to lookup the
next hop first and fall back to a full lookup if it fails (per the fix
4c9bcd117918b ("net: Fix nexthop lookups")).

Example:

    root@kenny:~# ip -6 ro ls table red
    local 2100:1::1 dev lo  proto none  metric 0  pref medium
    2100:1::/120 dev eth1  proto kernel  metric 256  pref medium
    local 2100:2::1 dev lo  proto none  metric 0  pref medium
    2100:2::/120 dev eth2  proto kernel  metric 256  pref medium
    local fe80::e0:f9ff:fe09:3cac dev lo  proto none  metric 0  pref medium
    local fe80::e0:f9ff:fe1c:b974 dev lo  proto none  metric 0  pref medium
    fe80::/64 dev eth1  proto kernel  metric 256  pref medium
    fe80::/64 dev eth2  proto kernel  metric 256  pref medium
    ff00::/8 dev red  metric 256  pref medium
    ff00::/8 dev eth1  metric 256  pref medium
    ff00::/8 dev eth2  metric 256  pref medium
    unreachable default dev lo  metric 240  error -113 pref medium

    root@kenny:~# ip -6 ro add table red 2100:3::/64 via 2100:1::64
    RTNETLINK answers: No route to host

Route add fails even though 2100:1::64 is a reachable next hop:
    root@kenny:~# ping6 -I red  2100:1::64
    ping6: Warning: source address might be selected on device other than red.
    PING 2100:1::64(2100:1::64) from 2100:1::1 red: 56 data bytes
    64 bytes from 2100:1::64: icmp_seq=1 ttl=64 time=1.33 ms

With this patch:
    root@kenny:~# ip -6 ro add table red 2100:3::/64 via 2100:1::64
    root@kenny:~# ip -6 ro ls table red
    local 2100:1::1 dev lo  proto none  metric 0  pref medium
    2100:1::/120 dev eth1  proto kernel  metric 256  pref medium
    local 2100:2::1 dev lo  proto none  metric 0  pref medium
    2100:2::/120 dev eth2  proto kernel  metric 256  pref medium
    2100:3::/64 via 2100:1::64 dev eth1  metric 1024  pref medium
    local fe80::e0:f9ff:fe09:3cac dev lo  proto none  metric 0  pref medium
    local fe80::e0:f9ff:fe1c:b974 dev lo  proto none  metric 0  pref medium
    fe80::/64 dev eth1  proto kernel  metric 256  pref medium
    fe80::/64 dev eth2  proto kernel  metric 256  pref medium
    ff00::/8 dev red  metric 256  pref medium
    ff00::/8 dev eth1  metric 256  pref medium
    ff00::/8 dev eth2  metric 256  pref medium
    unreachable default dev lo  metric 240  error -113 pref medium

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
v2
- addressed DaveM's comment that table lookup failure falls back to full
  lookup to be consistent with ipv4
- moved new code to a helper for better readability

 net/ipv6/route.c | 40 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 38 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d916d6ab9ad2..af46e19205f5 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1769,6 +1769,37 @@ static int ip6_convert_metrics(struct mx6_config *mxc,
 	return -EINVAL;
 }
 
+static struct rt6_info *ip6_nh_lookup_table(struct net *net,
+					    struct fib6_config *cfg,
+					    const struct in6_addr *gw_addr)
+{
+	struct flowi6 fl6 = {
+		.flowi6_oif = cfg->fc_ifindex,
+		.daddr = *gw_addr,
+		.saddr = cfg->fc_prefsrc,
+	};
+	struct fib6_table *table;
+	struct rt6_info *rt;
+	int flags = 0;
+
+	table = fib6_get_table(net, cfg->fc_table);
+	if (!table)
+		return NULL;
+
+	if (!ipv6_addr_any(&cfg->fc_prefsrc))
+		flags |= RT6_LOOKUP_F_HAS_SADDR;
+
+	rt = ip6_pol_route(net, table, cfg->fc_ifindex, &fl6, flags);
+
+	/* if table lookup failed, fall back to full lookup */
+	if (rt == net->ipv6.ip6_null_entry) {
+		ip6_rt_put(rt);
+		rt = NULL;
+	}
+
+	return rt;
+}
+
 static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg)
 {
 	struct net *net = cfg->fc_nlinfo.nl_net;
@@ -1940,7 +1971,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg)
 		rt->rt6i_gateway = *gw_addr;
 
 		if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) {
-			struct rt6_info *grt;
+			struct rt6_info *grt = NULL;
 
 			/* IPv6 strictly inhibits using not link-local
 			   addresses as nexthop address.
@@ -1952,7 +1983,12 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg)
 			if (!(gwa_type & IPV6_ADDR_UNICAST))
 				goto out;
 
-			grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, 1);
+			if (cfg->fc_table)
+				grt = ip6_nh_lookup_table(net, cfg, gw_addr);
+
+			if (!grt)
+				grt = rt6_lookup(net, gw_addr, NULL,
+						 cfg->fc_ifindex, 1);
 
 			err = -EHOSTUNREACH;
 			if (!grt)
-- 
2.1.4

             reply	other threads:[~2016-04-25  4:26 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-04-25  4:26 David Ahern [this message]
2016-04-27 19:37 ` [PATCH v2 net-next] net: ipv6: Use passed in table for nexthop lookups David Miller

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1461558364-17970-1-git-send-email-dsa@cumulusnetworks.com \
    --to=dsa@cumulusnetworks.com \
    --cc=netdev@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).