IPv6: Add "offload failed" indication to routes

After installing a route to the kernel, user space receives an
acknowledgment, which means the route was installed in the kernel, but not
necessarily in hardware.

The asynchronous nature of route installation in hardware can lead to a
routing daemon advertising a route before it was actually installed in
hardware. This can result in packet loss or mis-routed packets until the
route is installed in hardware.

To avoid such cases, previous patch set added the ability to emit
RTM_NEWROUTE notifications whenever RTM_F_OFFLOAD/RTM_F_TRAP flags
are changed, this behavior is controlled by sysctl.

With the above mentioned behavior, it is possible to know from user-space
if the route was offloaded, but if the offload fails there is no indication
to user-space. Following a failure, a routing daemon will wait indefinitely
for a notification that will never come.

This patch adds an "offload_failed" indication to IPv6 routes, so that
users will have better visibility into the offload process.

'struct fib6_info' is extended with new field that indicates if route
offload failed. Note that the new field is added using unused bit and
therefore there is no need to increase struct size.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index ac9a174372cccfad765b6d564d7b2a76b13d88fe..a5f980b6940e2d04eec46cfdc2aca3f035fedbe7 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -5008,7 +5008,7 @@ mlxsw_sp_fib6_entry_hw_flags_set(struct mlxsw_sp *mlxsw_sp,
                                  common);
        list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list)
                fib6_info_hw_flags_set(mlxsw_sp_net(mlxsw_sp), mlxsw_sp_rt6->rt,
-                                      should_offload, !should_offload);
+                                      should_offload, !should_offload, false);
 }
 #else
 static void
@@ -5030,7 +5030,7 @@ mlxsw_sp_fib6_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp,
                                  common);
        list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list)
                fib6_info_hw_flags_set(mlxsw_sp_net(mlxsw_sp), mlxsw_sp_rt6->rt,
-                                      false, false);
+                                      false, false, false);
 }
 #else
 static void

diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c
index ca19da169853871f5c42b4e30530b7ddc60e4cfd..6b1ec3b4750cf78315f032fd6a7e88e0219079a6 100644 (file)
--- a/drivers/net/netdevsim/fib.c
+++ b/drivers/net/netdevsim/fib.c
@@ -595,7 +595,7 @@ static void nsim_fib6_rt_hw_flags_set(struct nsim_fib_data *data,
        struct nsim_fib6_rt_nh *fib6_rt_nh;
 
        list_for_each_entry(fib6_rt_nh, &fib6_rt->nh_list, list)
-               fib6_info_hw_flags_set(net, fib6_rt_nh->rt, false, trap);
+               fib6_info_hw_flags_set(net, fib6_rt_nh->rt, false, trap, false);
 }
 #else
 static void nsim_fib6_rt_hw_flags_set(struct nsim_fib_data *data,

diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 1e262b23c68b4099d5c420300c79a32346def47a..15b7fbe6b15c28ef30ee7b578d3bc6d2aa368028 100644 (file)
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -195,7 +195,8 @@ struct fib6_info {
                                        fib6_destroying:1,
                                        offload:1,
                                        trap:1,
-                                       unused:2;
+                                       offload_failed:1,
+                                       unused:1;
 
        struct rcu_head                 rcu;
        struct nexthop                  *nh;
@@ -539,7 +540,7 @@ static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric)
        return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric));
 }
 void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i,
-                           bool offload, bool trap);
+                           bool offload, bool trap, bool offload_failed);
 
 #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL)
 struct bpf_iter__ipv6_route {

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0d1784b0d65df301a775434a21c866559ecb0bb6..bc75b705f54b910b322d507edd141e6d135c41ff 100644 (file)
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -5619,6 +5619,8 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
                        rtm->rtm_flags |= RTM_F_OFFLOAD;
                if (rt->trap)
                        rtm->rtm_flags |= RTM_F_TRAP;
+               if (rt->offload_failed)
+                       rtm->rtm_flags |= RTM_F_OFFLOAD_FAILED;
        }
 
        if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0)
@@ -6070,16 +6072,18 @@ errout:
 }
 
 void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i,
-                           bool offload, bool trap)
+                           bool offload, bool trap, bool offload_failed)
 {
        struct sk_buff *skb;
        int err;
 
-       if (f6i->offload == offload && f6i->trap == trap)
+       if (f6i->offload == offload && f6i->trap == trap &&
+           f6i->offload_failed == offload_failed)
                return;
 
        f6i->offload = offload;
        f6i->trap = trap;
+       f6i->offload_failed = offload_failed;
 
        if (!rcu_access_pointer(f6i->fib6_node))
                /* The route was removed from the tree, do not send