Merge branch 'ipv4-nexthop-link-status'

davem330 · davem330 · commit f389a40ec30f · 2015-06-24T02:16:03.000-07:00
Andy Gospodarek says:

====================
changes to make ipv4 routing table aware of next-hop link status

This series adds the ability to have the Linux kernel track whether or
not a particular route should be used based on the link-status of the
interface associated with the next-hop.

Before this patch any link-failure on an interface that was serving as a
gateway for some systems could result in those systems being isolated
from the rest of the network as the stack would continue to attempt to
send frames out of an interface that is actually linked-down.  When the
kernel is responsible for all forwarding, it should also be responsible
for taking action when the traffic can no longer be forwarded -- there
is no real need to outsource link-monitoring to userspace anymore.

This feature is only enabled with the new per-interface or ipv4 global
sysctls called 'ignore_routes_with_linkdown'.

net.ipv4.conf.all.ignore_routes_with_linkdown = 0
net.ipv4.conf.default.ignore_routes_with_linkdown = 0
net.ipv4.conf.lo.ignore_routes_with_linkdown = 0
...

When the above sysctls are set, the kernel will not only report to
userspace that the link is down, but it will also report to userspace
that a route is dead.  This will signal to userspace that the route will
not be selected.

With the new sysctls set, the following behavior can be observed
(interface p8p1 is link-down):

default via 10.0.5.2 dev p9p1
10.0.5.0/24 dev p9p1  proto kernel  scope link  src 10.0.5.15
70.0.0.0/24 dev p7p1  proto kernel  scope link  src 70.0.0.1
80.0.0.0/24 dev p8p1  proto kernel  scope link  src 80.0.0.1 dead linkdown
90.0.0.0/24 via 80.0.0.2 dev p8p1  metric 1 dead linkdown
90.0.0.0/24 via 70.0.0.2 dev p7p1  metric 2
90.0.0.1 via 70.0.0.2 dev p7p1  src 70.0.0.1
    cache
local 80.0.0.1 dev lo  src 80.0.0.1
    cache &lt;local&gt;
80.0.0.2 via 10.0.5.2 dev p9p1  src 10.0.5.15
    cache

While the route does remain in the table (so it can be modified if
needed rather than being wiped away as it would be if IFF_UP was
cleared), the proper next-hop is chosen automatically when the link is
down.  Now interface p8p1 is linked-up:

default via 10.0.5.2 dev p9p1
10.0.5.0/24 dev p9p1  proto kernel  scope link  src 10.0.5.15
70.0.0.0/24 dev p7p1  proto kernel  scope link  src 70.0.0.1
80.0.0.0/24 dev p8p1  proto kernel  scope link  src 80.0.0.1
90.0.0.0/24 via 80.0.0.2 dev p8p1  metric 1
90.0.0.0/24 via 70.0.0.2 dev p7p1  metric 2
192.168.56.0/24 dev p2p1  proto kernel  scope link  src 192.168.56.2
90.0.0.1 via 80.0.0.2 dev p8p1  src 80.0.0.1
    cache
local 80.0.0.1 dev lo  src 80.0.0.1
    cache &lt;local&gt;
80.0.0.2 dev p8p1  src 80.0.0.1
    cache

and the output changes to what one would expect.

If the global or interface sysctl is not set, the following output would
be expected when p8p1 is down:

default via 10.0.5.2 dev p9p1
10.0.5.0/24 dev p9p1  proto kernel  scope link  src 10.0.5.15
70.0.0.0/24 dev p7p1  proto kernel  scope link  src 70.0.0.1
80.0.0.0/24 dev p8p1  proto kernel  scope link  src 80.0.0.1 linkdown
90.0.0.0/24 via 80.0.0.2 dev p8p1  metric 1 linkdown
90.0.0.0/24 via 70.0.0.2 dev p7p1  metric 2

If the dead flag does not appear there should be no expectation that the
kernel would skip using this route due to link being down.

v2: Split kernel changes into 2 patches: first to add linkdown flag and
second to add new sysctl settings.  Also took suggestion from Alex to
simplify code by only checking sysctl during fib lookup and suggestion
from Scott to add a per-interface sysctl.  Added iproute2 patch to
recognize and print linkdown flag.

v3: Code cleanups along with reverse-path checks suggested by Alex and
small fixes related to problems found when multipath was disabled.

v4: Drop binary sysctls

v5: Whitespace and variable declaration fixups suggested by Dave

v6: Style changes noticed by Dave and checkpath suggestions.

v7: Last checkpatch fixup.

Though there were some that preferred not to have a configuration option
and to make this behavior the default when it was discussed in Ottawa
earlier this year since "it was time to do this."  I wanted to propose
the config option to preserve the current behavior for those that desire
it.  I'll happily remove it if Dave and Linus approve.

An IPv6 implementation is also needed (DECnet too!), but I wanted to
start with the IPv4 implementation to get people comfortable with the
idea before moving forward.  If this is accepted the IPv6 implementation
can be posted shortly.

There was also a request for switchdev support for this, but that will
be posted as a followup as switchdev does not currently handle dead
next-hops in a multi-path case and I felt that infra needed to be added
first.

FWIW, we have been running the original version of this series with a
global sysctl and our customers have been happily using a backported
version for IPv4 and IPv6 for &gt;6 months.
====================

Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
@@ -120,6 +120,9 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev)
 	 || (!IN_DEV_FORWARD(in_dev) && \
 	  IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS)))
 
+#define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \
+	IN_DEV_CONF_GET((in_dev), IGNORE_ROUTES_WITH_LINKDOWN)
+
 #define IN_DEV_ARPFILTER(in_dev)	IN_DEV_ORCONF((in_dev), ARPFILTER)
 #define IN_DEV_ARP_ACCEPT(in_dev)	IN_DEV_ORCONF((in_dev), ARP_ACCEPT)
 #define IN_DEV_ARP_ANNOUNCE(in_dev)	IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE)
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
@@ -36,7 +36,8 @@ struct fib_lookup_arg {
 	void			*result;
 	struct fib_rule		*rule;
 	int			flags;
-#define FIB_LOOKUP_NOREF	1
+#define FIB_LOOKUP_NOREF		1
+#define FIB_LOOKUP_IGNORE_LINKSTATE	2
 };
 
 struct fib_rules_ops {
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
@@ -226,15 +226,15 @@ static inline struct fib_table *fib_new_table(struct net *net, u32 id)
 }
 
 static inline int fib_lookup(struct net *net, const struct flowi4 *flp,
-			     struct fib_result *res)
+			     struct fib_result *res, unsigned int flags)
 {
 	struct fib_table *tb;
 	int err = -ENETUNREACH;
 
 	rcu_read_lock();
 
 	tb = fib_get_table(net, RT_TABLE_MAIN);
-	if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF))
+	if (tb && !fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF))
 		err = 0;
 
 	rcu_read_unlock();
@@ -249,28 +249,30 @@ void __net_exit fib4_rules_exit(struct net *net);
 struct fib_table *fib_new_table(struct net *net, u32 id);
 struct fib_table *fib_get_table(struct net *net, u32 id);
 
-int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res);
+int __fib_lookup(struct net *net, struct flowi4 *flp,
+		 struct fib_result *res, unsigned int flags);
 
 static inline int fib_lookup(struct net *net, struct flowi4 *flp,
-			     struct fib_result *res)
+			     struct fib_result *res, unsigned int flags)
 {
 	struct fib_table *tb;
 	int err;
 
+	flags |= FIB_LOOKUP_NOREF;
 	if (net->ipv4.fib_has_custom_rules)
-		return __fib_lookup(net, flp, res);
+		return __fib_lookup(net, flp, res, flags);
 
 	rcu_read_lock();
 
 	res->tclassid = 0;
 
 	for (err = 0; !err; err = -ENETUNREACH) {
 		tb = rcu_dereference_rtnl(net->ipv4.fib_main);
-		if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF))
+		if (tb && !fib_table_lookup(tb, flp, res, flags))
 			break;
 
 		tb = rcu_dereference_rtnl(net->ipv4.fib_default);
-		if (tb && !fib_table_lookup(tb, flp, res, FIB_LOOKUP_NOREF))
+		if (tb && !fib_table_lookup(tb, flp, res, flags))
 			break;
 	}
 
@@ -305,9 +307,9 @@ void fib_flush_external(struct net *net);
 
 /* Exported by fib_semantics.c */
 int ip_fib_check_default(__be32 gw, struct net_device *dev);
-int fib_sync_down_dev(struct net_device *dev, int force);
+int fib_sync_down_dev(struct net_device *dev, unsigned long event);
 int fib_sync_down_addr(struct net *net, __be32 local);
-int fib_sync_up(struct net_device *dev);
+int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
 void fib_select_multipath(struct fib_result *res);
 
 /* Exported by fib_trie.c */
diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h
@@ -164,6 +164,7 @@ enum
 	IPV4_DEVCONF_ROUTE_LOCALNET,
 	IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL,
 	IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL,
+	IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN,
 	__IPV4_DEVCONF_MAX
 };
 
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
@@ -338,6 +338,9 @@ struct rtnexthop {
 #define RTNH_F_PERVASIVE	2	/* Do recursive gateway lookup	*/
 #define RTNH_F_ONLINK		4	/* Gateway is forced on link	*/
 #define RTNH_F_OFFLOAD		8	/* offloaded route */
+#define RTNH_F_LINKDOWN		16	/* carrier-down on nexthop */
+
+#define RTNH_COMPARE_MASK	(RTNH_F_DEAD | RTNH_F_LINKDOWN)
 
 /* Macros to handle hexthops */
 
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
@@ -2169,6 +2169,8 @@ static struct devinet_sysctl_table {
 					"igmpv2_unsolicited_report_interval"),
 		DEVINET_SYSCTL_RW_ENTRY(IGMPV3_UNSOLICITED_REPORT_INTERVAL,
 					"igmpv3_unsolicited_report_interval"),
+		DEVINET_SYSCTL_RW_ENTRY(IGNORE_ROUTES_WITH_LINKDOWN,
+					"ignore_routes_with_linkdown"),
 
 		DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"),
 		DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"),
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
@@ -280,7 +280,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 		fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
 		fl4.flowi4_scope = scope;
 		fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0;
-		if (!fib_lookup(net, &fl4, &res))
+		if (!fib_lookup(net, &fl4, &res, 0))
 			return FIB_RES_PREFSRC(net, res);
 	} else {
 		scope = RT_SCOPE_LINK;
@@ -319,7 +319,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0;
 
 	net = dev_net(dev);
-	if (fib_lookup(net, &fl4, &res))
+	if (fib_lookup(net, &fl4, &res, 0))
 		goto last_resort;
 	if (res.type != RTN_UNICAST &&
 	    (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev)))
@@ -354,7 +354,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	fl4.flowi4_oif = dev->ifindex;
 
 	ret = 0;
-	if (fib_lookup(net, &fl4, &res) == 0) {
+	if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) {
 		if (res.type == RTN_UNICAST)
 			ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
 	}
@@ -1063,9 +1063,9 @@ static void nl_fib_lookup_exit(struct net *net)
 	net->ipv4.fibnl = NULL;
 }
 
-static void fib_disable_ip(struct net_device *dev, int force)
+static void fib_disable_ip(struct net_device *dev, unsigned long event)
 {
-	if (fib_sync_down_dev(dev, force))
+	if (fib_sync_down_dev(dev, event))
 		fib_flush(dev_net(dev));
 	rt_cache_flush(dev_net(dev));
 	arp_ifdown(dev);
@@ -1081,7 +1081,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 	case NETDEV_UP:
 		fib_add_ifaddr(ifa);
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-		fib_sync_up(dev);
+		fib_sync_up(dev, RTNH_F_DEAD);
 #endif
 		atomic_inc(&net->ipv4.dev_addr_genid);
 		rt_cache_flush(dev_net(dev));
@@ -1093,7 +1093,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 			/* Last address was deleted from this interface.
 			 * Disable IP.
 			 */
-			fib_disable_ip(dev, 1);
+			fib_disable_ip(dev, event);
 		} else {
 			rt_cache_flush(dev_net(dev));
 		}
@@ -1107,9 +1107,10 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct in_device *in_dev;
 	struct net *net = dev_net(dev);
+	unsigned int flags;
 
 	if (event == NETDEV_UNREGISTER) {
-		fib_disable_ip(dev, 2);
+		fib_disable_ip(dev, event);
 		rt_flush_dev(dev);
 		return NOTIFY_DONE;
 	}
@@ -1124,16 +1125,22 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 			fib_add_ifaddr(ifa);
 		} endfor_ifa(in_dev);
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-		fib_sync_up(dev);
+		fib_sync_up(dev, RTNH_F_DEAD);
 #endif
 		atomic_inc(&net->ipv4.dev_addr_genid);
 		rt_cache_flush(net);
 		break;
 	case NETDEV_DOWN:
-		fib_disable_ip(dev, 0);
+		fib_disable_ip(dev, event);
 		break;
-	case NETDEV_CHANGEMTU:
 	case NETDEV_CHANGE:
+		flags = dev_get_flags(dev);
+		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+			fib_sync_up(dev, RTNH_F_LINKDOWN);
+		else
+			fib_sync_down_dev(dev, event);
+		/* fall through */
+	case NETDEV_CHANGEMTU:
 		rt_cache_flush(net);
 		break;
 	}
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
@@ -47,11 +47,12 @@ struct fib4_rule {
 #endif
 };
 
-int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res)
+int __fib_lookup(struct net *net, struct flowi4 *flp,
+		 struct fib_result *res, unsigned int flags)
 {
 	struct fib_lookup_arg arg = {
 		.result = res,
-		.flags = FIB_LOOKUP_NOREF,
+		.flags = flags,
 	};
 	int err;
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
